for: optimize decision making systems in complex actor-based systems with sparse or uninformative feedback
methods: Hessian-aware Bayesian Optimization and compact multi-layered architecture modeling actor interactions
results: effective optimization under resource constraints and malformed feedback settings, as demonstrated on several benchmarksAbstract
Many approaches for optimizing decision making systems rely on gradient based methods requiring informative feedback from the environment. However, in the case where such feedback is sparse or uninformative, such approaches may result in poor performance. Derivative-free approaches such as Bayesian Optimization mitigate the dependency on the quality of gradient feedback, but are known to scale poorly in the high-dimension setting of complex decision making systems. This problem is exacerbated if the system requires interactions between several actors cooperating to accomplish a shared goal. To address the dimensionality challenge, we propose a compact multi-layered architecture modeling the dynamics of actor interactions through the concept of role. Additionally, we introduce Hessian-aware Bayesian Optimization to efficiently optimize the multi-layered architecture parameterized by a large number of parameters. Experimental results demonstrate that our method (HA-GP-UCB) works effectively on several benchmarks under resource constraints and malformed feedback settings.
摘要
很多决策系统优化方法 rely于梯度基于方法，需要环境提供有用的反馈。然而，在环境反馈稀缺或不具有信息时，这些方法可能会表现不佳。 derivative-free方法如极限优化 mitigate了对梯度反馈质量的依赖，但是在复杂决策系统中可能会Scales poorly。这个问题被加剧，当决策系统需要多个演员合作完成共同目标时。为了解决维度挑战，我们提议使用compact多层架构，模型演员之间的相互作用via角色概念。此外，我们引入了Hessian-aware极限优化，以高效地优化多层架构中的大量参数。实验结果表明，我们的方法（HA-GP-UCB）在资源限制和缺失反馈设置下工作有效。
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes
results: 该研究提出了一种基于多Modal数据输入的人体姿态估计算法，并通过评估多种模式的算法来证明该数据集的可靠性和挑战性。Abstract
3D human pose estimation in outdoor environments has garnered increasing attention recently. However, prevalent 3D human pose datasets pertaining to outdoor scenes lack diversity, as they predominantly utilize only one type of modality (RGB image or pointcloud), and often feature only one individual within each scene. This limited scope of dataset infrastructure considerably hinders the variability of available data. In this article, we propose Human-M3, an outdoor multi-modal multi-view multi-person human pose database which includes not only multi-view RGB videos of outdoor scenes but also corresponding pointclouds. In order to obtain accurate human poses, we propose an algorithm based on multi-modal data input to generate ground truth annotation. This benefits from robust pointcloud detection and tracking, which solves the problem of inaccurate human localization and matching ambiguity that may exist in previous multi-view RGB videos in outdoor multi-person scenes, and generates reliable ground truth annotations. Evaluation of multiple different modalities algorithms has shown that this database is challenging and suitable for future research. Furthermore, we propose a 3D human pose estimation algorithm based on multi-modal data input, which demonstrates the advantages of multi-modal data input for 3D human pose estimation. Code and data will be released on https://github.com/soullessrobot/Human-M3-Dataset.
摘要
Recently, 3D人体姿态估计在户外环境中获得了越来越多的关注。然而，现有的大多数3D人体姿态数据集，都是在户外场景中使用单一的感知模式（RGB图像或点云），并且通常只有一个人在每个场景中。这种限定的数据基础设施会很大程度上阻碍数据的变化。在这篇文章中，我们提出了人类-M3数据集，这是一个户外多模式多视图多人3D人体姿态数据集，包括不只是多视图RGB视频，还有对应的点云数据。为了获取准确的人体姿态，我们提议一种基于多modal数据输入的算法来生成基准注释。这种方法利用了Robust点云探测和跟踪，解决了在前一代多视图RGB视频中的人员Localization和匹配抖动问题，并生成了可靠的基准注释。多种不同的模式算法的评估表明，这个数据集是一个挑战性的和适用的研究工具。此外，我们还提出了基于多modal数据输入的3D人体姿态估计算法，这显示了多modal数据输入的优势。代码和数据将在GitHub上发布，请参考。
Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers
paper_authors: Alan Perotti, Simone Bertolotto, Eliana Pastor, André Panisson
for: 这篇论文旨在提高图像分类模型的解释性和可靠性，通过integrating semantic information into the training process。
methods: 该论文提出了一种通用的方法，可以从任何类型的semantic information中 derivate an additional loss term，以提高模型的解释性和可靠性。
results: 研究人员通过应用该方法，在图像分类器中提高了模型的解释性和可靠性，并且可以更好地理解模型的内部表示。Code repository可以在https://github.com/S1M0N38/semantic-encodings中找到。Abstract
Images are loaded with semantic information that pertains to real-world ontologies: dog breeds share mammalian similarities, food pictures are often depicted in domestic environments, and so on. However, when training machine learning models for image classification, the relative similarities amongst object classes are commonly paired with one-hot-encoded labels. According to this logic, if an image is labelled as 'spoon', then 'tea-spoon' and 'shark' are equally wrong in terms of training loss. To overcome this limitation, we explore the integration of additional goals that reflect ontological and semantic knowledge, improving model interpretability and trustworthiness. We suggest a generic approach that allows to derive an additional loss term starting from any kind of semantic information about the classification label. First, we show how to apply our approach to ontologies and word embeddings, and discuss how the resulting information can drive a supervised learning process. Second, we use our semantically enriched loss to train image classifiers, and analyse the trade-offs between accuracy, mistake severity, and learned internal representations. Finally, we discuss how this approach can be further exploited in terms of explainability and adversarial robustness. Code repository: https://github.com/S1M0N38/semantic-encodings
摘要
图像具有 semantic 信息，与实际世界 ontology 相关：狗种类共享哺乳动物相似之处，食物图片常出现在家庭环境中，等等。然而，在训练机器学习模型时，对象类之间的相似性通常通过一颗一颗的一频编码标签进行表示。根据这种逻辑，如果一个图像被标记为 '餐勺'，那么 '茶勺' 和 '鲨鱼' 在训练损失方面都是等错的。为了超越这些限制，我们探讨了 Semantic 和 ontology 知识的整合，以提高模型可解性和可信度。我们建议一种通用的方法，可以从任何类型的 semantic 信息开始， derivate 一个额外的损失项。我们首先介绍了如何应用我们的方法到 ontology 和 word embedding，然后讨论了如何通过这些信息驱动一个supervised learning 过程。其次，我们使用我们的含义整合的损失函数来训练图像分类器，并分析了精度、错误严重性和学习内部表示之间的交易。最后，我们讨论了如何进一步利用这种方法，以提高解释性和对抗训练的鲜明性。Code repository：https://github.com/S1M0N38/semantic-encodings。
Latent-Shift: Gradient of Entropy Helps Neural Codecs
results: 实验表明，利用梯度 entropy 可以获得 $1-2%$ 的压缩率下降，同时保持相同的质量。这种方法是独立的并且可以与其他改进方法结合使用。Abstract
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional techniques such as easy adaptation on perceptual distortion metrics and high performance on specific domains thanks to their learning ability. However, state of the art neural codecs does not take advantage of the existence of gradient of entropy in decoding device. In this paper, we theoretically show that gradient of entropy (available at decoder side) is correlated with the gradient of the reconstruction error (which is not available at decoder side). We then demonstrate experimentally that this gradient can be used on various compression methods, leading to a $1-2\%$ rate savings for the same quality. Our method is orthogonal to other improvements and brings independent rate savings.
摘要
通过端到端图像/视频编解码器来比较传统的压缩技术，这些可编程的编解码器具有许多优势，如容易适应人工引导的质量指标和高性能在特定领域，归功于其学习能力。然而，现代神经网络编解码器并没有利用解码器 сторо的梯度Entropy的存在。在这篇论文中，我们理论上表明，解码器 сторо的梯度Entropy和不可知的重建错误梯度之间存在相关性。然后，我们通过实验证明，这个梯度可以在不同的压缩方法上使用，导致1-2%的比较率节省，同时不会与其他改进方法冲突。
Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
results: 研究发现，在不同的正则化参数和训练时间下，吸引器神经网络的性能会在不同的梯度下降步长和训练时间下进行变化，并且可以通过调整正则化参数和早停策略来避免过拟合。Abstract
In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices turn out to be a class of matrices which correspond to Hebbian kernels revised by iteratively applying some unlearning protocols. Remarkably, the number of unlearning steps is proved to be related to the regularization hyperparameters of the loss function and to the training time. Thus, we can design strategies to avoid overfitting that are formulated in terms of the algebraic properties of the interaction matrix, or, equivalently, in terms of regularization tuning and early-stopping strategies. The generalization capabilities of these attractor networks are also investigated: analytical results are obtained for random synthetic datasets, next, the emerging picture is corroborated by numerical experiments that highlight the existence of several regimes (i.e., overfitting, failure and success) as the dataset parameters are varied.
摘要
在这个工作中，我们从机器学习角度来看征引导神经网络：我们通过应用梯度下降来找到优化的网络参数，并且在这个框架下，优化的神经元互动矩阵turns out to be一类具有HEBBbian kernel的修订版本，经过一系列的快速学习过程。很显然，这些快速学习步骤的数量与优化器的补偿参数以及训练时间有关。因此，我们可以通过对互动矩阵的代数性质进行设计，或者通过补偿参数的调整和早期停止策略来避免过拟合。此外，我们还 investigate了这些吸引器网络的泛化能力，通过对随机生成的 sintetic dataset进行分析，并且通过 numerical experiments corroborate the emerging picture, highlighting the existence of several regimes（i.e., overfitting, failure, and success）as the dataset parameters are varied.
Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel
results: 这个论文的实验结果表明，基于SVR的量子聚类预测模型（QSVR）在11个实验数据集中的含秘率和准确率都高于其他模型，并且在9个数据集中都高于量子自编码器（QAE）。Abstract
Anomaly detection (AD) involves identifying observations or events that deviate in some way from the rest of the data. Machine learning techniques have shown success in automating this process by detecting hidden patterns and deviations in large-scale data. The potential of quantum computing for machine learning has been widely recognized, leading to extensive research efforts to develop suitable quantum machine learning (QML) algorithms. In particular, the search for QML algorithms for near-term NISQ devices is in full swing. However, NISQ devices pose additional challenges due to their limited qubit coherence times, low number of qubits, and high error rates. Kernel methods based on quantum kernel estimation have emerged as a promising approach to QML on NISQ devices, offering theoretical guarantees, versatility, and compatibility with NISQ constraints. Especially support vector machines (SVM) utilizing quantum kernel estimation have shown success in various supervised learning tasks. However, in the context of AD, semisupervised learning is of great relevance, and yet there is limited research published in this area. This paper introduces an approach to semisupervised AD based on the reconstruction loss of a support vector regression (SVR) with quantum kernel. This novel model is an alternative to the variational quantum and quantum kernel one-class classifiers, and is compared to a quantum autoencoder as quantum baseline and a SVR with radial-basis-function (RBF) kernel as well as a classical autoencoder as classical baselines. The models are benchmarked extensively on 10 real-world AD data sets and one toy data set, and it is shown that our SVR model with quantum kernel performs better than the SVR with RBF kernel as well as all other models, achieving highest mean AUC over all data sets. In addition, our QSVR outperforms the quantum autoencoder on 9 out of 11 data sets.
摘要
异常检测（AD）涉及到从数据中找到不同的观察或事件。机器学习技术已经在自动化这个过程中得到了成功，通过检测大规模数据中的隐藏模式和偏差来检测异常。量子计算在机器学习方面的潜在优势已经得到了广泛的研究，并且在开发适合近期不稳定量子计算（NISQ）设备的量子机器学习（QML）算法方面进行了广泛的研究。然而，NISQ设备受限于寄存器准确时间、寄存器数量和错误率等因素，因此开发QML算法对NISQ设备的挑战。基于量子kernel估计的kernel方法在NISQ设备上的QML方面得到了广泛的关注，这种方法提供了理论保证、灵活性和NISQ约束的兼容性。特别是在检测方面，使用量子kernel估计的支持向量机（SVM）已经在多种监督学习任务中显示出成功。然而，在异常检测方面，半监督学习是非常有价值的，但是有限的研究出版在这个领域。本文提出了一种基于支持向量回归（SVR）的半监督异常检测方法，该方法使用量子kernel来估计异常点的权重。这种新的模型是对量子自变量和量子kernel一类的异常检测模型的一种替代方案，并与量子自变量和量子kernel一类的一类异常检测模型进行比较。我们对10个真实的异常检测数据集和1个玩偶数据集进行了广泛的 benchmarking，并证明了我们的SVR模型使用量子kernel在所有数据集上表现最佳，其中包括最高的平均AUC。此外，我们的QSVR模型在9个数据集中表现更好于量子自变量和RBF kernel的模型，并且在所有数据集上都表现得更好。
Graph Neural Networks for Forecasting Multivariate Realized Volatility with Spillover Effects
results: 研究发现，不考虑多个层次冲击效应并不提供明显的预测精度提高，但是模型非线性冲击效应可以提高实际波动预测精度，特别是在短期前一周内。此外，训练使用 quasi-likelihood 损失函数可以提高模型性能。Abstract
We present a novel methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks. The proposed model offers the benefits of incorporating spillover effects from multi-hop neighbors, capturing nonlinear relationships, and flexible training with different loss functions. Our empirical findings provide compelling evidence that incorporating spillover effects from multi-hop neighbors alone does not yield a clear advantage in terms of predictive accuracy. However, modeling nonlinear spillover effects enhances the forecasting accuracy of realized volatilities, particularly for short-term horizons of up to one week. Moreover, our results consistently indicate that training with the Quasi-likelihood loss leads to substantial improvements in model performance compared to the commonly-used mean squared error. A comprehensive series of empirical evaluations in alternative settings confirm the robustness of our results.
摘要
我们提出了一种新的方法来模型和预测多变量实现波动性，使用自定义图 neural network 来包含跨股波动效应。我们的模型具有以下优点：能够包含多 hop 邻居的波动效应，捕捉非线性关系，并且可以自由地训练不同的损失函数。我们的实验结果表明，单独通过多 hop 邻居的波动效应来模型并不能够提供明显的预测精度优势。然而，模型非线性波动效应可以提高实际波动性预测精度，特别是在短期 horizon 内，最多一周。此外，我们的结果一致地表明，使用 quasi-likelihood 损失函数进行训练可以与常用的mean squared error 损失函数相比，提高模型性能。我们在不同的设置中进行了完整的实验评估，并证明了我们的结果的稳定性。
Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
results: 研究使用了一个实际数据集，与相关文献进行比较，结果显示这种时间相依的推荐方法可以提高推荐的准确性和有效性。Abstract
Classical recommender systems often assume that historical data are stationary and fail to account for the dynamic nature of user preferences, limiting their ability to provide reliable recommendations in time-sensitive settings. This assumption is particularly problematic in finance, where financial products exhibit continuous changes in valuations, leading to frequent shifts in client interests. These evolving interests, summarized in the past client-product interactions, see their utility fade over time with a degree that might differ from one client to another. To address this challenge, we propose a time-dependent collaborative filtering algorithm that can adaptively discount distant client-product interactions using personalized decay functions. Our approach is designed to handle the non-stationarity of financial data and produce reliable recommendations by modeling the dynamic collaborative signals between clients and products. We evaluate our method using a proprietary dataset from BNP Paribas and demonstrate significant improvements over state-of-the-art benchmarks from relevant literature. Our findings emphasize the importance of incorporating time explicitly in the model to enhance the accuracy of financial product recommendation.
摘要
Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms
for: investigate the impact of test-time adversarial attacks on linear regression models and determine the optimal level of robustness that any model can reach while maintaining a given level of standard predictive performance (accuracy)
methods: use quantitative estimates to uncover fundamental tradeoffs between adversarial robustness and accuracy in different regimes, and obtain a precise characterization which distinguishes between regimes where robustness is achievable without hurting standard accuracy and regimes where a tradeoff might be unavoidable
results: empirically confirm the findings with simple experiments that represent a variety of settings, and extend beyond previous works in this area by considering feature covariance matrices and attack norms of any nature.Abstract
In this paper, we investigate the impact of test-time adversarial attacks on linear regression models and determine the optimal level of robustness that any model can reach while maintaining a given level of standard predictive performance (accuracy). Through quantitative estimates, we uncover fundamental tradeoffs between adversarial robustness and accuracy in different regimes. We obtain a precise characterization which distinguishes between regimes where robustness is achievable without hurting standard accuracy and regimes where a tradeoff might be unavoidable. Our findings are empirically confirmed with simple experiments that represent a variety of settings. This work applies to feature covariance matrices and attack norms of any nature, and extends beyond previous works in this area.
摘要
在这篇论文中，我们研究了在线性回归模型下的测试时对抗攻击的影响，并确定了保持给定水平的标准预测性能（准确率）的最佳鲁棒性水平。通过量化估计，我们揭示了不同情况下的基本负面关系 между鲁棒性和准确率。我们获得了精确的分类，可以分 distinguish between不同情况下的鲁棒性可以不受标准准确率的影响和可能不可避免的负面关系。我们的发现得到了Empirical验证，通过一些简单的实验来 represnt多种设定。这种工作适用于特征covariance矩阵和攻击norm的任何种类，并超越了过去在这一领域的工作。
Copula for Instance-wise Feature Selection and Ranking
methods: 利用 Gaussian copula 技术来捕捉特征之间的相关性，并将其integrated into 当前的特征选择框架中。
results: 通过实验证明，我们的方法可以更好地捕捉特征之间的相关性，并提高特征选择和排序的精度。Abstract
Instance-wise feature selection and ranking methods can achieve a good selection of task-friendly features for each sample in the context of neural networks. However, existing approaches that assume feature subsets to be independent are imperfect when considering the dependency between features. To address this limitation, we propose to incorporate the Gaussian copula, a powerful mathematical technique for capturing correlations between variables, into the current feature selection framework with no additional changes needed. Experimental results on both synthetic and real datasets, in terms of performance comparison and interpretability, demonstrate that our method is capable of capturing meaningful correlations.
摘要
实例化特征选择和排名方法可以在神经网络中实现每个样本的好选择特征。然而，现有的方法假设特征子集是独立的，这会导致忽略特征之间的相互关系。为了解决这种限制，我们提议在当前特征选择框架中 incorporate Gaussian copula，这是一种强大的数学技术，用于捕捉变量之间的相互关系。实验结果表明，我们的方法可以 Capture 有意义的相互关系。（简化中文）实例化特征选择和排名方法可以在神经网络中实现每个样本的好选择特征。然而，现有的方法假设特征子集是独立的，这会导致忽略特征之间的相互关系。为了解决这种限制，我们提议在当前特征选择框架中 incorporate Gaussian copula，这是一种强大的数学技术，用于捕捉变量之间的相互关系。实验结果表明，我们的方法可以 Capture 有意义的相互关系。
Predicting Early Dropouts of an Active and Healthy Ageing App
paper_authors: Vasileios Perifanis, Ioanna Michailidi, Giorgos Stamatelatos, George Drosatos, Pavlos S. Efraimidis
for: 预测年轻和健康老年人APP上的早期退出者
methods: 使用机器学习方法预测用户使用Dynamic和Static特征进行抵抗性预测
results: 机器学习算法可以提供高质量抵抗性预测结果，动态特征对模型分类性能有积极影响，使用SMOTE和ADASYN填充方法提高了分类性能10%。Abstract
In this work, we present a machine learning approach for predicting early dropouts of an active and healthy ageing app. The presented algorithms have been submitted to the IFMBE Scientific Challenge 2022, part of IUPESM WC 2022. We have processed the given database and generated seven datasets. We used pre-processing techniques to construct classification models that predict the adherence of users using dynamic and static features. We submitted 11 official runs and our results show that machine learning algorithms can provide high-quality adherence predictions. Based on the results, the dynamic features positively influence a model's classification performance. Due to the imbalanced nature of the dataset, we employed oversampling methods such as SMOTE and ADASYN to improve the classification performance. The oversampling approaches led to a remarkable improvement of 10\%. Our methods won first place in the IFMBE Scientific Challenge 2022.
摘要
在这项工作中，我们提出了一种机器学习方法，用于预测活老年人健康应用程序中的早期退出。我们的算法已经参加了IFMBE科学挑战2022，这是IUPESM WC 2022年度科学会议的一部分。我们处理了给定的数据库，生成了七个数据集。我们使用了预处理技术，构建了基于动态和静态特征的分类模型，以预测用户的遵从度。我们提交了11个官方运行，结果表明，机器学习算法可以提供高质量的遵从预测。基于结果，动态特征对模型的分类性能产生了积极的影响。由于数据集具有偏置的特点，我们使用了权重采样方法，如SMOTE和ADASYN，以改善分类性能。这些权重采样方法导致了10%的显著提升。我们的方法在IFMBE科学挑战2022中获得了第一名。
Graph Embedding Dynamic Feature-based Supervised Contrastive Learning of Transient Stability for Changing Power Grid Topologies
paper_authors: Zijian Lv, Xin Chen, Zijian Feng for: 本研究旨在提高电力系统稳定性预测精度，使其能够快速适应电力网 topology 变化。methods: 本研究提出了基于图 embedding 动态特征 (GEDF) 的超vised contrastive learning (SCL) 模型，使用 supervised contrastive learning 预测过渡稳定性，考虑到电力网 topology 信息。results: 测试结果表明，GEDF-SCL 模型可以高精度地预测过渡稳定性，并适应不同电力网 topology 变化。Abstract
Accurate online transient stability prediction is critical for ensuring power system stability when facing disturbances. While traditional transient stablity analysis replies on the time domain simulations can not be quickly adapted to the power grid toplogy change. In order to vectorize high-dimensional power grid topological structure information into low-dimensional node-based graph embedding streaming data, graph embedding dynamic feature (GEDF) has been proposed. The transient stability GEDF-based supervised contrastive learning (GEDF-SCL) model uses supervised contrastive learning to predict transient stability with GEDFs, considering power grid topology information. To evaluate the performance of the proposed GEDF-SCL model, power grids of varying topologies were generated based on the IEEE 39-bus system model. Transient operational data was obtained by simulating N-1 and N-$\bm{m}$-1 contingencies on these generated power system topologies. Test result demonstrated that the GEDF-SCL model can achieve high accuracy in transient stability prediction and adapt well to changing power grid topologies.
摘要
<>精准在线稳定预测是电力系统稳定性的关键因素，尤其是在面临干扰时。传统的稳定预测分析依赖于时间域 simulink cannot be quickly adapted to the power grid topology change. 为了vectorize高维电力网 topological structure信息到低维节点基于图像流动数据，图像嵌入动态特征（GEDF）已经提出。基于GEDF的稳定预测模型使用supervised contrastive learning（GEDF-SCL）来预测稳定性，考虑电力网 topology信息。为评估提出的GEDF-SCL模型表现，根据IEEE 39-bus系统模型生成了不同电力网 topology。通过对这些生成的电力系统 topology进行随机N-1和N-m-1的 simulate，获得了过渡操作数据。测试结果表明，GEDF-SCL模型可以高度准确地预测稳定性和适应变化的电力网 topology。<>
Graph Contrastive Learning with Generative Adversarial Network
results: 在七个实际数据集上实现高质量的数据增强和 twelve 个基线方法的超越。另外，发现生成的视图最终遵循网络上知名的偏好附加规则。Abstract
Graph Neural Networks (GNNs) have demonstrated promising results on exploiting node representations for many downstream tasks through supervised end-to-end training. To deal with the widespread label scarcity issue in real-world applications, Graph Contrastive Learning (GCL) is leveraged to train GNNs with limited or even no labels by maximizing the mutual information between nodes in its augmented views generated from the original graph. However, the distribution of graphs remains unconsidered in view generation, resulting in the ignorance of unseen edges in most existing literature, which is empirically shown to be able to improve GCL's performance in our experiments. To this end, we propose to incorporate graph generative adversarial networks (GANs) to learn the distribution of views for GCL, in order to i) automatically capture the characteristic of graphs for augmentations, and ii) jointly train the graph GAN model and the GCL model. Specifically, we present GACN, a novel Generative Adversarial Contrastive learning Network for graph representation learning. GACN develops a view generator and a view discriminator to generate augmented views automatically in an adversarial style. Then, GACN leverages these views to train a GNN encoder with two carefully designed self-supervised learning losses, including the graph contrastive loss and the Bayesian personalized ranking Loss. Furthermore, we design an optimization framework to train all GACN modules jointly. Extensive experiments on seven real-world datasets show that GACN is able to generate high-quality augmented views for GCL and is superior to twelve state-of-the-art baseline methods. Noticeably, our proposed GACN surprisingly discovers that the generated views in data augmentation finally conform to the well-known preferential attachment rule in online networks.
摘要
图 нейрон网络 (GNN) 已经在利用节点表示来完成多个下游任务的超vised end-to-end 训练中展现出了扎根的结果。为了解决实际应用中的标签稀缺问题，我们利用图对照学习 (GCL) 来训练 GNN WITH 有限或者even no 标签，通过最大化节点之间的相互信息来进行augmentation。然而，现有文献中 Ignore 了图的分布，导致在most cases 中 ignored unseen edges，这是我们在实际实验中观察到的。为此，我们提议在view生成时使用图生成随机网络 (GAN) 来学习图的分布，以便自动捕捉图的特性，并jointly 训练图GAN模型和GCL模型。我们称之为GACN，它包括一个视图生成器和一个视图分类器，通过对抗式的方式来生成自动化的视图。然后，GACN 利用这些视图来训练一个 GNN 编码器，并使用两种特制的自我超vised learning 损失函数，包括图对照学习损失和 Bayesian 个性化排序损失。此外，我们设计了一个优化框架，以便同时训练所有GACN模块。我们在七个实际数据集上进行了广泛的实验，发现GACN能够生成高质量的augmented views，并且在十二个基eline方法中表现出色。另外，我们发现GACN surprisingly 发现，生成的视图最终遵循了在线网络中的 preference attachment 规则。
A Novel Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction
results: 使用 uncertainty algorithm 构建多任务损失函数，在CitySim dataset上进行验证，TMMOE模型在预测车辆轨迹和驾驶意图方面具有最高的分类和回归结果，超过LSTM模型的性能。Abstract
Accurate Vehicle Trajectory Prediction is critical for automated vehicles and advanced driver assistance systems. Vehicle trajectory prediction consists of two essential tasks, i.e., longitudinal position prediction and lateral position prediction. There is a significant correlation between driving intentions and vehicle motion. In existing work, the three tasks are often conducted separately without considering the relationships between the longitudinal position, lateral position, and driving intention. In this paper, we propose a novel Temporal Multi-Gate Mixture-of-Experts (TMMOE) model for simultaneously predicting the vehicle trajectory and driving intention. The proposed model consists of three layers: a shared layer, an expert layer, and a fully connected layer. In the model, the shared layer utilizes Temporal Convolutional Networks (TCN) to extract temporal features. Then the expert layer is built to identify different information according to the three tasks. Moreover, the fully connected layer is used to integrate and export prediction results. To achieve better performance, uncertainty algorithm is used to construct the multi-task loss function. Finally, the publicly available CitySim dataset validates the TMMOE model, demonstrating superior performance compared to the LSTM model, achieving the highest classification and regression results. Keywords: Vehicle trajectory prediction, driving intentions Classification, Multi-task
摘要
准确的车辆轨迹预测是自动驾驶和高级驾驶助系统的关键。车辆轨迹预测包括两个基本任务： longitudinal position 预测和 lateral position 预测。车辆的运动和驾驶意图之间存在显著的相关性。在现有的工作中，这三个任务通常是分别进行的，没有考虑这三个任务之间的关系。在这篇论文中，我们提出了一种新的 Temporal Multi-Gate Mixture-of-Experts（TMMOE）模型，用于同时预测车辆轨迹和驾驶意图。该模型包括三层：共享层、专家层和全连接层。在模型中，共享层使用 Temporal Convolutional Networks（TCN）提取时间特征。然后专家层用于识别不同任务的信息。此外，全连接层用于集成和出口预测结果。为了提高性能，我们使用不确定算法构建多任务损失函数。最后，公共可用的 CitySim 数据集验证了 TMMOE 模型，并证明其与 LSTM 模型相比，达到了最高的分类和回归结果。关键词：车辆轨迹预测、驾驶意图分类、多任务
Variational Label-Correlation Enhancement for Congestion Prediction
paper_authors: Biao Liu, Congyu Qiao, Ning Xu, Xin Geng, Ziran Zhu, Jun Yang
for: This paper aims to improve the accuracy of congestion prediction in large-scale integrated circuit (IC) design by leveraging spatial label-correlation between neighboring grids.
methods: The proposed approach, called VAriational Label-Correlation Enhancement for Congestion Prediction ({\ours}), uses variational inference techniques to estimate a local label-correlation weight for each grid, which is influenced by the surrounding grids.
results: Experimental results on publicly available benchmarks demonstrate the superior effectiveness of {\ours} compared to existing methods.Here’s the simplified Chinese text:
results: 实验结果表明， compared to现有方法，{\ours}在公共可用的 \texttt{ISPD2011} 和 \texttt{DAC2012} benchmark上的效果更好。Abstract
The physical design process of large-scale designs is a time-consuming task, often requiring hours to days to complete, with routing being the most critical and complex step. As the the complexity of Integrated Circuits (ICs) increases, there is an increased demand for accurate routing quality prediction. Accurate congestion prediction aids in identifying design flaws early on, thereby accelerating circuit design and conserving resources. Despite the advancements in current congestion prediction methodologies, an essential aspect that has been largely overlooked is the spatial label-correlation between different grids in congestion prediction. The spatial label-correlation is a fundamental characteristic of circuit design, where the congestion status of a grid is not isolated but inherently influenced by the conditions of its neighboring grids. In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i.e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids. {\ours} leverages variational inference techniques to estimate this weight, thereby enhancing the regression model's performance by incorporating spatial dependencies. Experiment results validate the superior effectiveness of {\ours} on the public available \texttt{ISPD2011} and \texttt{DAC2012} benchmarks using the superblue circuit line.
摘要
大规模设计的物理设计过程是一项时间consuming任务，经常需要几天内完成，routing是最关键和复杂的步骤。随着集成电路（IC）的复杂度的提高，需要更加准确的堵塞质量预测。准确的堵塞预测可以早期发现设计缺陷，从而加速电路设计并保留资源。 DESPITE current congestion prediction methodologies advancements, an essential aspect that has been largely overlooked is the spatial label-correlation between different grids in congestion prediction. To fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, \ours, i.e., Variational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids. \ours leverages variational inference techniques to estimate this weight, thereby enhancing the regression model's performance by incorporating spatial dependencies. Experiment results validate the superior effectiveness of \ours on the publicly available \texttt{ISPD2011} and \texttt{DAC2012} benchmarks using the superblue circuit line.
Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
results: 在多中心（n=4）数据集中，与现有方法进行了广泛的评估和比较，并在外部测试集（n=3）中进行了统计分析，证明了该方法在临床实际中的有效性。 Developed的风险标记是全体生存率最强的预测因素之一，并且有可能与现有的临床因素相结合，以选择高风险患者，以便为其进行neoadjuvant therapy。Abstract
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer in which the tumor-vascular involvement greatly affects the resectability and, thus, overall survival of patients. However, current prognostic prediction methods fail to explicitly and accurately investigate relationships between the tumor and nearby important vessels. This paper proposes a novel learnable neural distance that describes the precise relationship between the tumor and vessels in CT images of different patients, adopting it as a major feature for prognosis prediction. Besides, different from existing models that used CNNs or LSTMs to exploit tumor enhancement patterns on dynamic contrast-enhanced CT imaging, we improved the extraction of dynamic tumor-related texture features in multi-phase contrast-enhanced CT by fusing local and global features using CNN and transformer modules, further enhancing the features extracted across multi-phase CT images. We extensively evaluated and compared the proposed method with existing methods in the multi-center (n=4) dataset with 1,070 patients with PDAC, and statistical analysis confirmed its clinical effectiveness in the external test set consisting of three centers. The developed risk marker was the strongest predictor of overall survival among preoperative factors and it has the potential to be combined with established clinical factors to select patients at higher risk who might benefit from neoadjuvant therapy.
摘要
胆囊ductal adenocarcinoma (PDAC) 是一种高度致命的癌症，肿瘤与邻近重要血管的交互影响了手术可能性和病人的全局生存率。然而，现有的预后预测方法无法详细和准确地探讨肿瘤和邻近重要血管之间的关系。这篇文章提出了一种新的学习型对应距离，用于描述不同病人的CT图像中肿瘤和血管之间的精确关系。此外，我们将对CT图像进行多相对对应的组合，以提高肿瘤相关的动态细胞特征的抽取。我们广泛评估和比较了提案方法与现有方法，在多中心（n=4）的数据集中进行了1,070名PDAC患者的评估，并统计分析确认了其临床效iveness。我们发展的预后标志是PDAC患者的预后因素中最强的预测因素，它有可能与已知的临床因素相结合，以选择需要neoadjuvant therapy的病人。
Explainable Graph Spectral Clustering of Text Documents
results: 本文经过实验研究，发现 $K $-embedding 可以很好地 Approximate Laplacian embedding，并且在某些条件下，这种近似性足够好。Abstract
Spectral clustering methods are known for their ability to represent clusters of diverse shapes, densities etc. However, results of such algorithms, when applied e.g. to text documents, are hard to explain to the user, especially due to embedding in the spectral space which has no obvious relation to document contents. Therefore there is an urgent need to elaborate methods for explaining the outcome of the clustering. This paper presents a contribution towards this goal. We present a proposal of explanation of results of combinatorial Laplacian based graph spectral clustering. It is based on showing (approximate) equivalence of combinatorial Laplacian embedding, $K$-embedding (proposed in this paper) and term vector space embedding. Hence a bridge is constructed between the textual contents and the clustering results. We provide theoretical background for this approach. We performed experimental study showing that $K$-embedding approximates well Laplacian embedding under favourable block matrix conditions and show that approximation is good enough under other conditions.
摘要
spectral clustering 方法知名于其能够表示多样化形态、密度等等的群集。然而，当应用于文档时，这些算法的结果难以向用户解释，特别是因为它们在spectral space中嵌入，这个空间与文档内容无法直接关联。因此，有一个急需要开发解释 clustering 结果的方法。本文提出了一种解释 combinatorial Laplacian 基于图 spectral clustering 的方法。这种方法基于显示（approximate）combinatorial Laplacian embedding、K-embedding（本文提出的）和term vector space embedding之间的等价性。因此， constructed 一个桥梁，将文本内容与 clustering 结果相连。我们提供了理论背景，并进行了实验研究，证明 K-embedding 可以在有利的块矩阵条件下高度准确地 aproximate Laplacian embedding。
DINO-CXR: A self supervised method based on vision transformer for chest X-ray classification
paper_authors: Mohammadreza Shakouri, Fatemeh Iranmanesh, Mahdi Eftekhari for: 本研究旨在提高骨肉X线成像分类的精度，探讨了一种基于自我指导学习的方法，即DINO-CXR。methods: 本研究使用了一种基于视觉变换器的自我指导学习方法，即DINO，并对其进行了修改，以适应骨肉X线成像分类。results: 对比分析表明，提出的方法在肺炎和COVID-19检测中具有更高的准确率，而且与现有方法相比，需要更少的标注数据来达到相同的准确率和AUC分数。Abstract
The limited availability of labeled chest X-ray datasets is a significant bottleneck in the development of medical imaging methods. Self-supervised learning (SSL) can mitigate this problem by training models on unlabeled data. Furthermore, self-supervised pretraining has yielded promising results in visual recognition of natural images but has not been given much consideration in medical image analysis. In this work, we propose a self-supervised method, DINO-CXR, which is a novel adaptation of a self-supervised method, DINO, based on a vision transformer for chest X-ray classification. A comparative analysis is performed to show the effectiveness of the proposed method for both pneumonia and COVID-19 detection. Through a quantitative analysis, it is also shown that the proposed method outperforms state-of-the-art methods in terms of accuracy and achieves comparable results in terms of AUC and F-1 score while requiring significantly less labeled data.
摘要
限量的胸部X射线数据的可用性是医学影像方法的发展中的一个重要瓶颈。自我超vised学习（SSL）可以解决这个问题，通过训练模型在无标签数据上。此外，自我超vised预训练在自然图像的视觉识别中已经产生了有望的结果，但在医学影像分析中尚未得到了充分的关注。本文提出了一种自我超vised方法，称为DINO-CXR，该方法是基于视transformer的胸部X射线分类的一种新的适应。通过对比分析，本文证明了提议的方法在肺炎和COVID-19检测中的效果。通过量化分析，还表明了提议的方法在准确率和AUC和F-1分数方面比现有方法高，而且需要远少于标注数据。
Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
paper_authors: Phuong Quynh Le, Jörg Schlötterer, Christin Seifert
for: 提高预测模型在具有相关性的样本集中的准确率
methods: 使用深度特征重新权重（DFR）方法，只需重新训练类фика器的最后一层
results: 对具有相关性的医疗数据进行实验，发现DFR可以提高预测模型的准确率，但是仍然容易受到偶极性关系的影响Abstract
Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but lack causal reasoning. This behavior particularly degrades accuracy in groups of samples of the correlated class that are missing the spurious feature or samples of the opposite class but with the spurious feature present. The recently proposed Deep Feature Reweighting (DFR) method improves accuracy of these worst groups. Based on the main argument that ERM mods can learn core features sufficiently well, DFR only needs to retrain the last layer of the classification model with a small group-balanced data set. In this work, we examine the applicability of DFR to realistic data in the medical domain. Furthermore, we investigate the reasoning behind the effectiveness of last-layer retraining and show that even though DFR has the potential to improve the accuracy of the worst group, it remains susceptible to spurious correlations.
摘要
模型通过实际风险最小化（ERM）训练而学习依赖于假冒特征，即其预测基于与类别标签强相关的非正常特征，而不具备 causal 理解。这种行为特别是在类别标签相关的样本群中 missing 假冒特征或 opposing 类别标签并具备假冒特征时，精度会减退。 reciently proposed Deep Feature Reweighting（DFR）方法可以改善这些最差的组的精度。基于主要的 argue that ERM mods can learn core features well enough, DFR only needs to retrain the last layer of the classification model with a small group-balanced dataset. 在这项工作中，我们检查了 DFR 在实际数据上的可行性，并进一步调查了 last-layer 重新训练的效果，并证明了 DFR 具有改善最差组精度的潜在能力，但它仍然受到假冒关系的影响。
for: This paper focuses on the theory of zeroth-order optimization, specifically on algorithms that approximate gradient and Hessian information using zeroth-order queries.
methods: The proposed algorithm in the paper is called \texttt{MiNES} (mirror descent natural evolution strategy), which is designed to minimize a reparameterized objective function that approximates the original objective function’s gradient and Hessian information.
results: The paper shows that the estimated covariance matrix of \texttt{MiNES} converges to the inverse of the Hessian matrix of the objective function with a convergence rate of $\widetilde{\mathcal{O}(1/k)$, where $k$ is the iteration number. Additionally, the paper provides explicit convergence rates for \texttt{MiNES} and explains how the covariance matrix promotes the convergence rate.Here is the information in Simplified Chinese text:
for: 本 paper 关注的是零次ORDER优化理论，特别是使用零次ORDER查询来 aproximate 函数值差的算法。
results: paper 显示了 \texttt{MiNES} 的 estimated covariance matrix 与原始函数的Hessian矩阵 inverse 的渐近关系，具体来说， convergence rate 是 $\widetilde{\mathcal{O}(1/k)$，其中 $k$ 是迭代次数。Abstract
The zeroth-order optimization has been widely used in machine learning applications. However, the theoretical study of the zeroth-order optimization focus on the algorithms which approximate (first-order) gradients using (zeroth-order) function value difference at a random direction. The theory of algorithms which approximate the gradient and Hessian information by zeroth-order queries is much less studied. In this paper, we focus on the theory of zeroth-order optimization which utilizes both the first-order and second-order information approximated by the zeroth-order queries. We first propose a novel reparameterized objective function with parameters $(\mu, \Sigma)$. This reparameterized objective function achieves its optimum at the minimizer and the Hessian inverse of the original objective function respectively, but with small perturbations. Accordingly, we propose a new algorithm to minimize our proposed reparameterized objective, which we call \texttt{MiNES} (mirror descent natural evolution strategy). We show that the estimated covariance matrix of \texttt{MiNES} converges to the inverse of Hessian matrix of the objective function with a convergence rate $\widetilde{\mathcal{O}(1/k)$, where $k$ is the iteration number and $\widetilde{\mathcal{O}(\cdot)$ hides the constant and $\log$ terms. We also provide the explicit convergence rate of \texttt{MiNES} and how the covariance matrix promotes the convergence rate.
摘要
“零次优化已经广泛应用于机器学习领域。然而，关于零次优化的理论研究主要集中在approximate（首次）梯度使用（零次）函数值差异的Random Direction中。在这篇论文中，我们将关注零次优化中使用首次和第二次信息的approximation的理论。我们首先提出一个新的重parameterized objective function with parameters（μ, Σ）。这个重parameterized objective function在原始目标函数的最小值和原始目标函数的Hessian inverse的两个点上均 achieves its optimum，但受到小幅度的干扰。 accordingly, we propose a new algorithm to minimize our proposed reparameterized objective, which we call \texttt{MiNES} (mirror descent natural evolution strategy). we show that the estimated covariance matrix of \texttt{MiNES} converges to the inverse of Hessian matrix of the objective function with a convergence rate $\widetilde{\mathcal{O}(1/k)$, where $k$ is the iteration number and $\widetilde{\mathcal{O}(\cdot)$ hides the constant and $\log$ terms. we also provide the explicit convergence rate of \texttt{MiNES} and how the covariance matrix promotes the convergence rate.”Note: The translation is done using Google Translate and may not be perfect. Please let me know if you need any further assistance.
Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example
results: 研究发现，无论选择哪些参数，Adam 算法在这个简单的一维函数上都会导致散射。Abstract
A very simple unidimensional function with Lipschitz continuous gradient is constructed such that the ADAM algorithm with constant stepsize, started from the origin, diverges when applied to minimize this function in the absence of noise on the gradient. Divergence occurs irrespective of the choice of the method parameters.
摘要
一个非常简单的一维函数，其梯度 lipschitz 连续，被构造了，使得在缺失梯度误差情况下，使用 ADAM 算法的常数步长开始从原点进行拟合，将导致异常。这种异常不管选择算法参数的方式，都会发生。
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models
results: 通过 MajorCert 算法，可以确保样本不会被小 patch 的修改 manipulate 深度学习模型预测错误的标签。Abstract
Patch robustness certification ensures no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques cannot certify samples that cannot meet their strict bars at the classifier or patch region levels. This paper proposes MajorCert. MajorCert firstly finds all possible label sets manipulatable by the same patch region on the same sample across the underlying classifiers, then enumerates their combinations element-wise, and finally checks whether the majority invariant of all these combinations is intact to certify samples.
摘要
patch 强健证明ensure no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques cannot certify samples that cannot meet their strict bars at the classifier or patch region levels. This paper proposes MajorCert. MajorCert firstly finds all possible label sets manipulatable by the same patch region on the same sample across the underlying classifiers, then enumerates their combinations element-wise, and finally checks whether the majority invariant of all these combinations is intact to certify samples.Here's the word-for-word translation:patch 强健证明ensure no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques cannot certify samples that cannot meet their strict bars at the classifier or patch region levels. This paper proposes MajorCert. MajorCert firstly finds all possible label sets manipulatable by the same patch region on the same sample across the underlying classifiers, then enumerates their combinations element-wise, and finally checks whether the majority invariant of all these combinations is intact to certify samples.Note that the translation is in Simplified Chinese, which is the standard form of Chinese used in mainland China and Singapore. If you need Traditional Chinese, please let me know.
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers
results: 对于一个action recognition benchmark dataset，模型表现出色，证明了将音频和视频 modalities结合在一起可以提高action recognition的效果。Abstract
In line with the human capacity to perceive the world by simultaneously processing and integrating high-dimensional inputs from multiple modalities like vision and audio, we propose a novel model, MAiVAR-T (Multimodal Audio-Image to Video Action Recognition Transformer). This model employs an intuitive approach for the combination of audio-image and video modalities, with a primary aim to escalate the effectiveness of multimodal human action recognition (MHAR). At the core of MAiVAR-T lies the significance of distilling substantial representations from the audio modality and transmuting these into the image domain. Subsequently, this audio-image depiction is fused with the video modality to formulate a unified representation. This concerted approach strives to exploit the contextual richness inherent in both audio and video modalities, thereby promoting action recognition. In contrast to existing state-of-the-art strategies that focus solely on audio or video modalities, MAiVAR-T demonstrates superior performance. Our extensive empirical evaluations conducted on a benchmark action recognition dataset corroborate the model's remarkable performance. This underscores the potential enhancements derived from integrating audio and video modalities for action recognition purposes.
摘要
按照人类对世界的同时处理和 интеGRATE多模态输入的能力，我们提议一种新的模型，MAiVAR-T（多modal Audio-Image to Video Action Recognition Transformer）。这个模型使用直观的方法将音频-图像和视频模态结合，以提高多modal human action recognition（MHAR）的效果。MAiVAR-T的核心思想是将音频模态中的重要表示转化到图像领域，然后将这些图像表示与视频模态进行融合。这种结合方法可以利用音频和视频模态中的上下文丰富性，从而提高动作识别。与现有的状态 искус法策略相比，MAiVAR-T表现出色。我们对一个标准动作识别数据集进行了广泛的实验，结果证明MAiVAR-T的出色表现。这不仅证明了将音频和视频模态结合的潜在提升，还证明了MAiVAR-T的优秀性。
Fair Models in Credit: Intersectional Discrimination and the Amplification of Inequity
paper_authors: Savina Kim, Stefan Lessmann, Galina Andreeva, Michael Rovatsos
For: The paper aims to examine intersectional horizontal inequities in credit access and demonstrate how pluralistic realities and intersectional identities can shape patterns of credit allocation when using automated decision-making systems.* Methods: The authors use data from the Spanish microfinance market to analyze credit allocation patterns and demonstrate the impact of algorithmic bias on vulnerable groups. They utilize the intersectionality paradigm to examine how multiple and intersecting social categories can interact to produce inequities in credit access.* Results: The study finds that while fairness may exist superficially, unfairness can exacerbate at lower levels given combinatorial effects. The authors demonstrate that sensitive attributes such as single parent status and number of children can result in imbalanced harm. They discuss the implications of these findings for the financial services industry.Here are the three points in Simplified Chinese text:* For: 这个论文的目的是检查并评估微贷市场中的多元性水平不平等，以及自动决策系统如何影响弱势群体的借款访问。* Methods: 作者们使用西班牙微贷市场的数据来分析借款分配的 patterns，并通过 интерсе克циональ paradigm来检查不同社会类别之间的交叠作用，以产生借款访问不平等。* Results: 研究发现，尽管 superfic 的公平可能存在，但是在更深层次上，不公平可能会加剧，即 comb 的效果。作者们发现，敏感属性如单身状态和子女数量可能会导致不平等的害。他们讨论这些发现对金融服务业的影响。Abstract
The increasing usage of new data sources and machine learning (ML) technology in credit modeling raises concerns with regards to potentially unfair decision-making that rely on protected characteristics (e.g., race, sex, age) or other socio-economic and demographic data. The authors demonstrate the impact of such algorithmic bias in the microfinance context. Difficulties in assessing credit are disproportionately experienced among vulnerable groups, however, very little is known about inequities in credit allocation between groups defined, not only by single, but by multiple and intersecting social categories. Drawing from the intersectionality paradigm, the study examines intersectional horizontal inequities in credit access by gender, age, marital status, single parent status and number of children. This paper utilizes data from the Spanish microfinance market as its context to demonstrate how pluralistic realities and intersectional identities can shape patterns of credit allocation when using automated decision-making systems. With ML technology being oblivious to societal good or bad, we find that a more thorough examination of intersectionality can enhance the algorithmic fairness lens to more authentically empower action for equitable outcomes and present a fairer path forward. We demonstrate that while on a high-level, fairness may exist superficially, unfairness can exacerbate at lower levels given combinatorial effects; in other words, the core fairness problem may be more complicated than current literature demonstrates. We find that in addition to legally protected characteristics, sensitive attributes such as single parent status and number of children can result in imbalanced harm. We discuss the implications of these findings for the financial services industry.
摘要
随着新数据源和机器学习技术在借款评估中的使用，有关可能存在不公正决策的问题减受到关注，这些决策可能基于保护特征（如种族、性别、年龄）或其他社会经济和民生数据。作者们在微贷上下文中展示了算法偏见的影响。借款评估困难更加折射在投降群体中，但现实上几乎没有关于借款分配不公的研究。本研究基于交叉性理论，研究借款访问不公平的现象，包括按照年龄、性别、婚姻状况、单身状况和子女数来分类。这篇论文使用西班牙微贷市场为背景，通过自动决策系统来探讨多元社会和交叉性识别如何影响借款分配的 patrón。由于机器学习技术对社会好坏无所谓，我们发现通过交叉性来检查算法公平性可以更加 authentically 使ower 动作，以实现更公平的结果。我们发现，虽然在高层次上，公平可能存在披露，但是在 combinatorial effects 下，不公正可能加剧，即核心公平问题可能更复杂。我们发现，除了法律保护的特征之外，敏感特征如单身状况和子女数也可能导致不均衡的危害。我们讨论了这些发现对金融服务业的影响。
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
paper_authors: Ning Miao, Yee Whye Teh, Tom Rainforth
for: 本研究旨在探讨 LLMs 是否可以自动认知自己的错误，不需要外部资源。
methods: 我们提出了一种零shot验证方法来识别错误，并用其进行权重投票来提高问答表现。
results: 我们在三个数学数据集上进行测试，发现该方法可以成功识别错误，并在最终预测性能中提高表现。Abstract
The recent progress in large language models (LLMs), especially the invention of chain-of-thoughts (CoT) prompting, makes it possible to solve reasoning problems. However, even the strongest LLMs are still struggling with more complicated problems that require non-linear thinking and multi-step reasoning. In this work, we explore whether LLMs have the ability to recognize their own errors, without resorting to external resources. In particular, we investigate whether they can be used to identify individual errors within a step-by-step reasoning. To this end, we propose a zero-shot verification scheme to recognize such errors. We then use this verification scheme to improve question-answering performance, by using it to perform weighted voting on different generated answers. We test the method on three math datasets-GSM8K, MathQA, and MATH-and find that it successfully recognizes errors and, in turn, increases final predictive performance.
摘要
最近很多大语言模型（LLMs）的进步，特别是创造思维（CoT）的提示，使得解释问题变得可能。然而，即使最强的LLMs仍然在更复杂的问题上遇到困难，需要非线性思维和多步逻辑。在这种情况下，我们询问LLMs是否有能力自动发现自己的错误，而不需要外部资源。特别是，我们研究LLMs是否可以用于识别单个步骤逻辑中的错误。为此，我们提出了零shot验证方案，用于识别such errors。然后，我们使用这种验证方案来提高问答表现，通过对不同生成的答案进行权重投票。我们在三个数学 dataset（GSM8K、MathQA和MATH）上测试了这种方法，并发现它成功地识别了错误，并在最终预测性能中提高了表现。
qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation
paper_authors: Stan van der Linde, Willem de Kok, Tariq Bontekoe, Sebastian Feld
for: 这篇论文是为了提高现代量子计算机的硬件限制下的量子电路编译过程的优化。
methods: 这篇论文使用了人工智能技术，具体来说是强化学习（RL），来优化量子电路编译过程。
results: 这篇论文提出了一个名为qgym的软件框架，该框架可以在高度可定制的环境中训练和测试RL算法和代理。Abstract
Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.
摘要
compile quantum circuit specific quantum hardware 是一个复杂的任务。此外，当前的量子计算机有严重的硬件限制。为了最大化有限资源，编译过程应该进行优化。为了改进当前方法，我们可以使用Reinforcement Learning（RL），这是一种 Agent 与环境互动以学习复杂的策略，以达到特定目标。在这项工作中，我们提出了qgym，一个基于 OpenAI gym 的软件框架，同时与量子编译环境相关。qgym 的目标是将人工智能（AI）与量子编译领域连接起来，抽象不相关的部分，以便在高度可定制的环境中训练和测试 RL 代理和算法。
Learning to Generate Training Datasets for Robust Semantic Segmentation
results: 对提案的生成模型进行了深入的研究，评估下游分割网络的性能和Robustness，并证明了该方法可以在真实世界的干扰和数据分布变化中显著提高semantic segmentation技术的Robustness。Abstract
Semantic segmentation techniques have shown significant progress in recent years, but their robustness to real-world perturbations and data samples not seen during training remains a challenge, particularly in safety-critical applications. In this paper, we propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design and train Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed or outlier images that can be used to train reliable segmentation models. We conduct in-depth studies of the proposed generative model, assess the performance and robustness of the downstream segmentation network, and demonstrate that our approach can significantly enhance the robustness of semantic segmentation techniques in the face of real-world perturbations, distribution shifts, and out-of-distribution samples. Our results suggest that this approach could be valuable in safety-critical applications, where the reliability of semantic segmentation techniques is of utmost importance and comes with a limited computational budget in inference. We will release our code shortly.
摘要
Semantic segmentation技术在最近几年内已经取得了显著的进步，但它们对实际世界中的干扰和训练数据集之外的数据样本仍然是一个挑战，特别是在安全关键应用中。在这篇论文中，我们提出了一种新的方法，以利用标签到图像生成器和图像到标签分割模型之间的共同作用，以提高 semantic segmentation 技术的可靠性。我们设计并训练了 Robusta，一种新的可靠 conditional generative adversarial network，以生成真实和可能的干扰或异常图像，用于训练可靠的分割模型。我们进行了深入的研究，评估了下游分割网络的性能和可靠性，并证明了我们的方法可以在实际世界中增强 semantic segmentation 技术的Robustness，包括分布转换、干扰和异常样本。我们的结果表明，这种方法在安全关键应用中可以提供有价值的技术，其可靠性和计算成本在推断中具有限制。我们即将发布我们的代码。
BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization
results: 在MuJoCo和Box2D任务中，BiERL frameworks比基eline和其他基eline都提高了学习性能，并且可以适应多种ERL算法。Abstract
Evolutionary reinforcement learning (ERL) algorithms recently raise attention in tackling complex reinforcement learning (RL) problems due to high parallelism, while they are prone to insufficient exploration or model collapse without carefully tuning hyperparameters (aka meta-parameters). In the paper, we propose a general meta ERL framework via bilevel optimization (BiERL) to jointly update hyperparameters in parallel to training the ERL model within a single agent, which relieves the need for prior domain knowledge or costly optimization procedure before model deployment. We design an elegant meta-level architecture that embeds the inner-level's evolving experience into an informative population representation and introduce a simple and feasible evaluation of the meta-level fitness function to facilitate learning efficiency. We perform extensive experiments in MuJoCo and Box2D tasks to verify that as a general framework, BiERL outperforms various baselines and consistently improves the learning performance for a diversity of ERL algorithms.
摘要
Tackling Hallucinations in Neural Chart Summarization
results: 通过人工评估，我们的方法显著减少了幻觉现象，并且改善了总体性能。Abstract
Hallucinations in text generation occur when the system produces text that is not grounded in the input. In this work, we tackle the problem of hallucinations in neural chart summarization. Our analysis shows that the target side of chart summarization training datasets often contains additional information, leading to hallucinations. We propose a natural language inference (NLI) based method to preprocess the training data and show through human evaluation that our method significantly reduces hallucinations. We also found that shortening long-distance dependencies in the input sequence and adding chart-related information like title and legends improves the overall performance.
摘要
文本生成中的幻觉现象发生在系统生成的文本与输入没有匹配。在这项工作中，我们解决了chart摘要 neural网络中的幻觉问题。我们的分析显示目标一侧chart摘要训练数据经常包含额外信息，导致幻觉。我们提议使用自然语言推理（NLI）基本方法来处理训练数据，并通过人工评估显示我们的方法可以显著减少幻觉。此外，我们发现短缩长距离相互关系在输入序列中和添加图表标题和图例可以提高总性表现。
A Survey of Time Series Anomaly Detection Methods in the AIOps Domain
results: 本文通过对一些实际应用场景的分析和评估，总结了时间序列异常检测的挑战和机遇，并提出了未来研究的方向和策略。Abstract
Internet-based services have seen remarkable success, generating vast amounts of monitored key performance indicators (KPIs) as univariate or multivariate time series. Monitoring and analyzing these time series are crucial for researchers, service operators, and on-call engineers to detect outliers or anomalies indicating service failures or significant events. Numerous advanced anomaly detection methods have emerged to address availability and performance issues. This review offers a comprehensive overview of time series anomaly detection in Artificial Intelligence for IT operations (AIOps), which uses AI capabilities to automate and optimize operational workflows. Additionally, it explores future directions for real-world and next-generation time-series anomaly detection based on recent advancements.
摘要
互联网基于服务的时间序列状态监控和分析已经取得了杰出的成功，生成了大量监控关键性表现指标 (KPI) 的时间序列。这些时间序列的监控和分析是研究人员、服务运营商和升级工程师需要侦测异常或异常状态的关键工具。多种高级异常探测方法已经出现，以解决可用性和性能问题。本评论提供了AI操作 (AIOps) 中时间序列异常探测的全面概述，并探讨未来领域和下一代时间序列异常探测的未来发展。
Counterfactual Graph Transformer for Traffic Flow Prediction
paper_authors: Ying Yang, Kai Du, Xingyuan Dai, Jianwu Fang
for: traffic flow prediction (TFP) in Intelligent Transportation System (ITS)
methods: graph-based models with multiple attention mechanisms, perturbation mask generator for counterfactual explanations
results: improved and interpretable traffic flow prediction, reliable explanations on three real-world public datasetsAbstract
Traffic flow prediction (TFP) is a fundamental problem of the Intelligent Transportation System (ITS), as it models the latent spatial-temporal dependency of traffic flow for potential congestion prediction. Recent graph-based models with multiple kinds of attention mechanisms have achieved promising performance. However, existing methods for traffic flow prediction tend to inherit the bias pattern from the dataset and lack interpretability. To this end, we propose a Counterfactual Graph Transformer (CGT) model with an instance-level explainer (e.g., finding the important subgraphs) specifically designed for TFP. We design a perturbation mask generator over input sensor features at the time dimension and the graph structure on the graph transformer module to obtain spatial and temporal counterfactual explanations. By searching the optimal perturbation masks on the input data feature and graph structures, we can obtain the concise and dominant data or graph edge links for the subsequent TFP task. After re-training the utilized graph transformer model after counterfactual perturbation, we can obtain improved and interpretable traffic flow prediction. Extensive results on three real-world public datasets show that CGT can produce reliable explanations and is promising for traffic flow prediction.
摘要
做为智能交通系统（ITS）的基础问题，流量流动预测（TFP）模型了路面交通流量的隐藏空间时间相依性，以预测潜在堵塞。现有的图形基本模型和多种注意力机制已经获得了显著的性能。然而，现有的交通流量预测方法通常会从数据集 inherit 偏见模式和缺乏解释性。为了解决这个问题，我们提出了Counterfactual Graph Transformer（CGT）模型，并特别设计了实例阶层解释器（例如，发现重要的子图）。我们在图形变换模组中实现了对输入感应器特征和图形结构的损害莳制生成器，以获得空间和时间的对应替代解释。通过寻找最佳的损害莳制，我们可以获得整体和主要的数据或图形边线，并将其用于后续的TFP任务。经过重新训练utilized graph transformer模型，我们可以获得改进和可解释的交通流量预测。实验结果显示，CGT可以生成可靠的解释和是TFP预测的有前途。
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning
results: 实验结果表明， RiFT 可以在 ResNet18、ResNet34 和 WideResNet34-10 模型上提高普适性和对抗性，同时保持或者甚至提高对抗性。Abstract
Deep neural networks are susceptible to adversarial examples, posing a significant security risk in critical applications. Adversarial Training (AT) is a well-established technique to enhance adversarial robustness, but it often comes at the cost of decreased generalization ability. This paper proposes Robustness Critical Fine-Tuning (RiFT), a novel approach to enhance generalization without compromising adversarial robustness. The core idea of RiFT is to exploit the redundant capacity for robustness by fine-tuning the adversarially trained model on its non-robust-critical module. To do so, we introduce module robust criticality (MRC), a measure that evaluates the significance of a given module to model robustness under worst-case weight perturbations. Using this measure, we identify the module with the lowest MRC value as the non-robust-critical module and fine-tune its weights to obtain fine-tuned weights. Subsequently, we linearly interpolate between the adversarially trained weights and fine-tuned weights to derive the optimal fine-tuned model weights. We demonstrate the efficacy of RiFT on ResNet18, ResNet34, and WideResNet34-10 models trained on CIFAR10, CIFAR100, and Tiny-ImageNet datasets. Our experiments show that \method can significantly improve both generalization and out-of-distribution robustness by around 1.5% while maintaining or even slightly enhancing adversarial robustness. Code is available at https://github.com/microsoft/robustlearn.
摘要
深度神经网络容易受到攻击性例子的威胁，这对重要应用场景来说是一个 significiant 的安全隐患。对此，抗击例（AT）是一种广泛使用的技术，可以提高攻击性 robustness，但它经常会导致模型的泛化能力减退。本文提出了一种新的方法，即 Robustness Critical Fine-Tuning（RiFT），可以增强泛化而不需要牺牲攻击性 robustness。RiFT 的核心思想是利用模型对 robustness 的剩余容量，通过精细调整对攻击性训练的模型中的非 robust-critical 模块的参数来增强泛化。为此，我们引入模块抗性评估（MRC），它评估模型对 worst-case веса变化的抗性。我们使用 MRC measure identificificate 模型中最低 MRC 值的模块为非 robust-critical 模块，然后精细调整其参数以获得精细调整后的参数。最后，我们将 adversarially trained weights 和精细调整后的 weights 线性 interpolate 以 derive 最佳 fine-tuned 模型 weights。我们在 ResNet18、ResNet34 和 WideResNet34-10 模型上进行 CIFAR10、CIFAR100 和 Tiny-ImageNet 数据集的实验，结果显示，\method 可以在泛化和离域 robustness 方面提高约 1.5%，同时保持或甚至提高攻击性 robustness。代码可以在 https://github.com/microsoft/robustlearn 上找到。
Shape Completion with Prediction of Uncertain Regions
for: Shape completion for robotic manipulation, specifically predicting the complete geometry of an object from a partial observation, and providing an indication of severe geometric uncertainty in extended regions.
methods: Two novel methods for predicting uncertain regions, one through postprocessing occupancy scores and the other through direct prediction of an uncertainty indicator, as well as two known approaches to probabilistic shape completion.
results: Both novel methods outperform the two baselines in shape completion and uncertain region prediction, and avoiding the predicted uncertain regions increases the quality of grasps for all tested methods.Here’s the text in Simplified Chinese:
for: shape completion for robotic manipulation, 特别是从受限的观察中预测物体的完整几何结构。
results: 这两种新方法在形成完整的几何结构和不确定区域预测方面都高于两个基eline方法，并且避免预测的不确定区域可以提高所有测试方法中的抓取质量。Abstract
Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of real grasps on object shape reconstruction, an indication of severe geometric uncertainty is indispensable. In particular, there can be an irreducible uncertainty in extended regions about the presence of entire object parts when given ambiguous object views. To treat this important case, we propose two novel methods for predicting such uncertain regions as straightforward extensions of any method for predicting local spatial occupancy, one through postprocessing occupancy scores, the other through direct prediction of an uncertainty indicator. We compare these methods together with two known approaches to probabilistic shape completion. Moreover, we generate a dataset, derived from ShapeNet, of realistically rendered depth images of object views with ground-truth annotations for the uncertain regions. We train on this dataset and test each method in shape completion and prediction of uncertain regions for known and novel object instances and on synthetic and real data. While direct uncertainty prediction is by far the most accurate in the segmentation of uncertain regions, both novel methods outperform the two baselines in shape completion and uncertain region prediction, and avoiding the predicted uncertain regions increases the quality of grasps for all tested methods. Web: https://github.com/DLR-RM/shape-completion
摘要
shape completion，即从partial observation中预测完整的物体形态，对机器人操作具有重要意义。当基于物体形态重建计划或预测实际抓取时，对物体形态的不确定性是不可或缺的。特别是在给出杂乱的物体视图时，可能存在扩展区域中对物体部分的存在是不确定的。为解决这个重要的问题，我们提出了两种新的方法，一种是通过处理占用度分布来预测不确定区域，另一种是直接预测不确定指标。我们将这些方法与两种已知方法进行比较，并在shape completion和不确定区域预测中进行测试。结果显示，直接预测不确定区域是最准确的 segmentation 方法，而我们的两种新方法在shape completion和不确定区域预测中均超过了两个基eline方法，并且避免预测的不确定区域可以提高所有测试方法的抓取质量。详细信息可以查看我们的github仓库：https://github.com/DLR-RM/shape-completion。
MRQ:Support Multiple Quantization Schemes through Model Re-Quantization
results: 这篇论文的结果显示，可以使用新开发的重新量化算法（包括权重调整和几何误差折衣）将MobileNetV2 QAT模型（[7]）转换为不同的量化方案（例如：对称和对称+二进制数值），单位损失不大于0.64单位。此外，这些量化模型已经成功地在NNA上部署在Echo Show设备上。Abstract
Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model quantization frameworks like Tensorflow QAT [1], TFLite PTQ [2], and Qualcomm AIMET [3] supports only a limited set of quantization schemes (e.g., only asymmetric per-tensor quantization in TF1.x QAT [4]). Accordingly, deep learning models cannot be easily quantized for diverse fixed-point hardwares, mainly due to slightly different quantization requirements. In this paper, we envision a new type of model quantization approach called MRQ (model re-quantization), which takes existing quantized models and quickly transforms the models to meet different quantization requirements (e.g., asymmetric -> symmetric, non-power-of-2 scale -> power-of-2 scale). Re-quantization is much simpler than quantizing from scratch because it avoids costly re-training and provides support for multiple quantization schemes simultaneously. To minimize re-quantization error, we developed a new set of re-quantization algorithms including weight correction and rounding error folding. We have demonstrated that MobileNetV2 QAT model [7] can be quickly re-quantized into two different quantization schemes (i.e., symmetric and symmetric+power-of-2 scale) with less than 0.64 units of accuracy loss. We believe our work is the first to leverage this concept of re-quantization for model quantization and models obtained from the re-quantization process have been successfully deployed on NNA in the Echo Show devices.
摘要
尽管现有多种各种硬件加速器（如NPU、TPU、DPU），但将深度学习模型部署到边缘设备上的固定点硬件仍然是一项复杂的挑战，主要是因为复杂的模型减quantization和转换。现有的模型减quantization框架，如TensorFlow QAT [1]、TFLite PTQ [2]和Qualcomm AIMET [3]，只支持一定的减quantization方案（如TF1.x QAT [4]中的只有非对称每个tensor减quantization）。因此，深度学习模型难以被容易减quantization，主要是因为不同的固定点硬件有些微的不同减quantization需求。在这篇论文中，我们提出了一种新的模型减quantization方法，称为MRQ（模型重新减quantization）。它可以将现有的减quantized模型快速地转换成符合不同减quantization需求的模型。重新减quantization比从头开始减quantization更加简单，因为它可以避免费时的重新训练，并且可以同时支持多种减quantization方案。为了减少重新减quantization的误差，我们开发了一组新的重新减quantization算法，包括权重修正和圆拟误差折衔。我们已经证明了，通过MRQ方法，可以快速地将MobileNetV2 QAT模型 [7] 转换成两种不同的减quantization方案（即Symmetric和Symmetric+power-of-2 scale），减少误差丢失不到0.64个单位。我们认为，我们的工作是首次利用这种重新减quantization概念来实现模型减quantization，并且已经成功部署了模型在NNA上的Echo Show设备。
Learning Green’s Function Efficiently Using Low-Rank Approximations
methods: 使用低级别分解学习绿函数，实现 removing redundant computations by separate learning with domain data for evaluation and Monte-Carlo samples for integral approximation
results: 提高计算时间，与 PINNs 和 MOD-Net 的准确率相似Abstract
Learning the Green's function using deep learning models enables to solve different classes of partial differential equations. A practical limitation of using deep learning for the Green's function is the repeated computationally expensive Monte-Carlo integral approximations. We propose to learn the Green's function by low-rank decomposition, which results in a novel architecture to remove redundant computations by separate learning with domain data for evaluation and Monte-Carlo samples for integral approximation. Using experiments we show that the proposed method improves computational time compared to MOD-Net while achieving comparable accuracy compared to both PINNs and MOD-Net.
摘要
使用深度学习模型学习格林函数，可以解决不同类型的部分 diferencial equation。 however，使用深度学习 для格林函数有一个实际的限制，即多次计算成本高的Monte-Carlo integral approximation。我们提议通过低级别 decompositions 学习格林函数，这会导致一种新的架构，可以通过分离学习领域数据和Monte-Carlo 样本来移除重复的计算。我们通过实验表明，我们的方法可以比MOD-Net快速计算，并且与PINNs和MOD-Net的准确率相当。
Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
results: 比对前一些动态方法和静态 adversarial 训练模型，提出的方法可以实现显著的鲁棒性提高而不损失精度。Abstract
The deep neural network has attained significant efficiency in image recognition. However, it has vulnerable recognition robustness under extensive data uncertainty in practical applications. The uncertainty is attributed to the inevitable ambient noise and, more importantly, the possible adversarial attack. Dynamic methods can effectively improve the defense initiative in the arms race of attack and defense of adversarial examples. Different from the previous dynamic method depend on input or decision, this work explore the dynamic attributes in model level through dynamic ensemble selection technology to further protect the model from white-box attacks and improve the robustness. Specifically, in training phase the Dirichlet distribution is apply as prior of sub-models' predictive distribution, and the diversity constraint in parameter space is introduced under the lightweight sub-models to construct alternative ensembel model spaces. In test phase, the certain sub-models are dynamically selected based on their rank of uncertainty value for the final prediction to ensure the majority accurate principle in ensemble robustness and accuracy. Compared with the previous dynamic method and staic adversarial traning model, the presented approach can achieve significant robustness results without damaging accuracy by combining dynamics and diversity property.
摘要
深度神经网络在图像识别中已经实现了显著的效率，但它在实际应用中面临着广泛的数据不确定性和可能的敌意攻击的问题。这些不确定性的来源包括不可避免的环境噪声以及可能的敌意攻击。动态方法可以有效地提高模型的防御力，在攻击和防御敌意例子的武器库中进行了反应。与之前的动态方法不同，本工作通过在模型层次上进行动态ensemble选择技术来进一步保护模型免受白盒攻击，提高了模型的Robustness。在训练阶段，我们使用Dirichlet分布作为子模型预测分布的PRIOR，并在轻量级子模型之间引入多样性约束，以构建多个备用模型空间。在测试阶段，根据它们的uncertainty值排名，选择一些特定的子模型来进行最终预测，以确保多数准确原理在ensemble robustness和精度之间达到平衡。与之前的动态方法和静态敌意训练模型相比，提出的方法可以无需损害精度而实现显著的Robustness。
Monitoring Algorithmic Fairness under Partial Observations
results: 这篇论文的实验结果显示，使用这些监控技术可以实现实时监控机器学习系统的公平性，并且可以在不同的实际应用中进行适当的调整。Abstract
As AI and machine-learned software are used increasingly for making decisions that affect humans, it is imperative that they remain fair and unbiased in their decisions. To complement design-time bias mitigation measures, runtime verification techniques have been introduced recently to monitor the algorithmic fairness of deployed systems. Previous monitoring techniques assume full observability of the states of the (unknown) monitored system. Moreover, they can monitor only fairness properties that are specified as arithmetic expressions over the probabilities of different events. In this work, we extend fairness monitoring to systems modeled as partially observed Markov chains (POMC), and to specifications containing arithmetic expressions over the expected values of numerical functions on event sequences. The only assumptions we make are that the underlying POMC is aperiodic and starts in the stationary distribution, with a bound on its mixing time being known. These assumptions enable us to estimate a given property for the entire distribution of possible executions of the monitored POMC, by observing only a single execution. Our monitors observe a long run of the system and, after each new observation, output updated PAC-estimates of how fair or biased the system is. The monitors are computationally lightweight and, using a prototype implementation, we demonstrate their effectiveness on several real-world examples.
摘要
As AI和机器学习软件在做决策时越来越多，它们必须保持公平和无偏见。为了补充设计时的偏见缓解措施，运行时监测技术已经在最近引入了。 previous监测技术假设了监测系统的完整可见性，并且只能监测已知的系统状态。在这种情况下，我们将公平监测扩展到采用partially observed Markov chains（POMC）模型的系统，并将特定的公平性特性表示为数值函数的期望值。我们假设了这个POMC是无限期的，并且知道其混合时间的上限。这些假设使我们能够估计整个可能的执行情况下的公平性，只需观察一个执行。我们的监测器在系统中观察长时间，每次新的观察结果出现后，输出了更新后的PAC估计值，用于评估系统的公平性。我们的监测器 computationally lightweight，并且使用原型实现，我们在实际应用中证明了它们的有效性。
Threshold-aware Learning to Generate Feasible Solutions for Mixed Integer Programs
For: The paper is written to address the challenge of finding high-quality feasible solutions to combinatorial optimization (CO) problems within a limited time, using machine learning (ML) methods.* Methods: The paper proposes a post-hoc method and a learning-based approach for optimizing the coverage of partial discrete variable assignments in Mixed Integer Programs (MIP), which bridges the gap between the learning and MIP objectives. The approach involves jointly learning to restrict the coverage search space and to predict the coverage in the learned search space, using a deep neural network.* Results: The paper demonstrates state-of-the-art performance in NeurIPS ML4CO datasets, achieving an optimality gap of 0.45% in the workload apportionment dataset within a one-minute time limit, which is a ten-fold improvement over SCIP.Abstract
Finding a high-quality feasible solution to a combinatorial optimization (CO) problem in a limited time is challenging due to its discrete nature. Recently, there has been an increasing number of machine learning (ML) methods for addressing CO problems. Neural diving (ND) is one of the learning-based approaches to generating partial discrete variable assignments in Mixed Integer Programs (MIP), a framework for modeling CO problems. However, a major drawback of ND is a large discrepancy between the ML and MIP objectives, i.e., variable value classification accuracy over primal bound. Our study investigates that a specific range of variable assignment rates (coverage) yields high-quality feasible solutions, where we suggest optimizing the coverage bridges the gap between the learning and MIP objectives. Consequently, we introduce a post-hoc method and a learning-based approach for optimizing the coverage. A key idea of our approach is to jointly learn to restrict the coverage search space and to predict the coverage in the learned search space. Experimental results demonstrate that learning a deep neural network to estimate the coverage for finding high-quality feasible solutions achieves state-of-the-art performance in NeurIPS ML4CO datasets. In particular, our method shows outstanding performance in the workload apportionment dataset, achieving the optimality gap of 0.45%, a ten-fold improvement over SCIP within the one-minute time limit.
摘要
寻找一个高质量可行的解决方案 для combinatorial optimization (CO) 问题在有限时间内是挑战的，主要因为其离散性。近年来，machine learning (ML) 方法在Addressing CO problems 问题上增加了。Neural diving (ND) 是一种学习基于的方法，用于生成混合整数程序（MIP）中的部分不连续变量分配。然而，ND 的一个主要缺点是ML 和 MIP 目标之间的大差异，即变量值分类准确率 над primal bound。我们的研究发现，在特定的变量分配率（coverage）范围内，可以获得高质量可行的解决方案，我们建议优化coverage来bridging the gap between learning和MIP目标。因此，我们提出了一种后续方法和一种学习基于的方法来优化coverage。我们的方法的关键思想是同时学习 restriction the coverage search space和在学习的搜索空间中预测coverage。实验结果表明，通过学习深度神经网络来估算coverage可以在 NeurIPS ML4CO 数据集中实现状态机器人的性能。特别是，我们的方法在工作负担分配数据集中表现出色，实现了1分钟时限内的优化性能，与SCIP相比，提高了10倍。
Pixel to policy: DQN Encoders for within & cross-game reinforcement learning
for: The paper aims to improve the performance of reinforcement learning (RL) models by leveraging transfer learning and multi-task learning in various game environments.
methods: The authors use deep Q-networks (DQN) as the RL model and explore different approaches of transfer learning, including pre-training the model on one game and fine-tuning it on another, as well as training the model on multiple games simultaneously.
results: The authors achieve impressive performance on several game environments, including a mean episode reward of 46.16, which beats human-level performance with only 20k episodes, and mean rewards of 533.42 and 402.17 on the Assault and Space Invader environments, respectively.Abstract
Reinforcement Learning can be applied to various tasks, and environments. Many of these environments have a similar shared structure, which can be exploited to improve RL performance on other tasks. Transfer learning can be used to take advantage of this shared structure, by learning policies that are transferable across different tasks and environments and can lead to more efficient learning as well as improved performance on a wide range of tasks. This work explores as well as compares the performance between RL models being trained from the scratch and on different approaches of transfer learning. Additionally, the study explores the performance of a model trained on multiple game environments, with the goal of developing a universal game-playing agent as well as transfer learning a pre-trained encoder using DQN, and training it on the same game or a different game. Our DQN model achieves a mean episode reward of 46.16 which even beats the human-level performance with merely 20k episodes which is significantly lower than deepmind's 1M episodes. The achieved mean rewards of 533.42 and 402.17 on the Assault and Space Invader environments respectively, represent noteworthy performance on these challenging environments.
摘要
“强化学习可以应用到多种任务和环境中，许多这些环境具有类似的共享结构，可以利用这些共享结构来提高强化学习性能。转移学习可以在不同任务和环境中学习可以转移的策略，从而实现更高效的学习以及多种任务的改进性能。本研究探讨了强化学习模型从零开始学习和转移学习的不同方法的性能，以及将多个游戏环境训练的模型在不同游戏中的性能。我们的DQN模型在46.16的平均回合奖励上达到了人类水平性能，只需20k个回合，这比深梦的1M个回合要低得多。在Assault和Space Invader环境中，我们的模型分别获得了533.42和402.17的平均奖励，这些表现在这些复杂的环境中是非常出色的。”
Doubly Robust Instance-Reweighted Adversarial Training
results: 在标准分类 dataset 上比基eline方法提高了平均防御性能，同时提高了最弱数据点的鲁棒性。Abstract
Assigning importance weights to adversarial data has achieved great success in training adversarially robust networks under limited model capacity. However, existing instance-reweighted adversarial training (AT) methods heavily depend on heuristics and/or geometric interpretations to determine those importance weights, making these algorithms lack rigorous theoretical justification/guarantee. Moreover, recent research has shown that adversarial training suffers from a severe non-uniform robust performance across the training distribution, e.g., data points belonging to some classes can be much more vulnerable to adversarial attacks than others. To address both issues, in this paper, we propose a novel doubly-robust instance reweighted AT framework, which allows to obtain the importance weights via exploring distributionally robust optimization (DRO) techniques, and at the same time boosts the robustness on the most vulnerable examples. In particular, our importance weights are obtained by optimizing the KL-divergence regularized loss function, which allows us to devise new algorithms with a theoretical convergence guarantee. Experiments on standard classification datasets demonstrate that our proposed approach outperforms related state-of-the-art baseline methods in terms of average robust performance, and at the same time improves the robustness against attacks on the weakest data points. Codes will be available soon.
摘要
<>使用对抗数据中的重要性权重进行训练，已经在有限模型容量下实现了很大的成功。然而，现有的实例权重对抗训练（AT）方法仍然依赖于各种euristic和/或几何解释来确定这些重要性权重，使得这些算法缺乏正式的理论基础和保证。此外，现有研究表明，对抗训练受到训练分布中的非均匀攻击性影响，例如，某些类型的数据点可能更容易受到攻击。为解决这两个问题，在本文中，我们提出了一种新的双重稳健实例权重AT框架，可以通过探索分布式稳健优化（DRO）技术来获得重要性权重，并在同时提高最容易受到攻击的数据点的稳健性。具体来说，我们的重要性权重通过优化KL散度规范化损失函数来获得，这使我们可以开发新的算法，并提供了理论上的准确性保证。实验表明，我们的提议方法在标准分类 datasets 上的平均Robust性性能高于相关的状态艺术基eline方法，同时在最容易受到攻击的数据点上提高了稳健性。代码即将上传。
GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
results: 我们的方法可以减少平均假阳性率，比现有方法提高True Positive Rate（TPR）的性能。在95%假阳性率（FPR95）下，我们的方法可以减少OOD数据的假阳性率达8%。Abstract
Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient space information to derive OOD scores neglecting the role of most important parameters of the pre-trained network over in-distribution (ID) data. In this study, we propose a novel approach called GradOrth to facilitate OOD detection based on one intriguing observation that the important features to identify OOD data lie in the lower-rank subspace of in-distribution (ID) data. In particular, we identify OOD data by computing the norm of gradient projection on the subspaces considered important for the in-distribution data. A large orthogonal projection value (i.e. a small projection value) indicates the sample as OOD as it captures a weak correlation of the ID data. This simple yet effective method exhibits outstanding performance, showcasing a notable reduction in the average false positive rate at a 95% true positive rate (FPR95) of up to 8% when compared to the current state-of-the-art methods.
摘要
检测不同领域（OOD）数据是机器学习模型在实际应用中安全部署的关键。然而，现有的OOD检测方法主要基于特征图或整个梯度空间信息来 derive OOD 分数，忽略了预训练网络中最重要的参数的作用。在本研究中，我们提出了一种新的方法called GradOrth，用于基于ID数据中最重要的特征进行OOD检测。具体来说，我们通过计算ID数据中考虑重要的特征SUBSPACE上的梯度 projetcion norm来识别OOD数据。如果梯度 проекcion norm值很小（即梯度 проекcion 强度很弱），则表示该样本是OOD数据。这种简单 yet有效的方法在评估中显示了remarkable performance，与当前状态的方法相比，可以达到8%的 False Positive Rate（FPR）降低。
Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks
methods: 提出了一种图基于的通用编码方案，考虑了材料层和设备层的嵌入，同时还引入了一种新的空间关系嵌入， inspirited by interpolation operations typically used in finite element meshing。
results: 通过利用物理法则和数据驱动模拟，实现了Surrogate Poisson 优化和current-voltage（IV）预测，并使用了一种新的图注意力网络（RelGAT）。Abstract
An innovative methodology that leverages artificial intelligence (AI) and graph representation for semiconductor device encoding in TCAD device simulation is proposed. A graph-based universal encoding scheme is presented that not only considers material-level and device-level embeddings, but also introduces a novel spatial relationship embedding inspired by interpolation operations typically used in finite element meshing. Universal physical laws from device simulations are leveraged for comprehensive data-driven modeling, which encompasses surrogate Poisson emulation and current-voltage (IV) prediction based on drift-diffusion model. Both are achieved using a novel graph attention network, referred to as RelGAT. Comprehensive technical details based on the device simulator Sentaurus TCAD are presented, empowering researchers to adopt the proposed AI-driven Electronic Design Automation (EDA) solution at the device level.
摘要
一种创新的方法ология，利用人工智能（AI）和图表示法来实现半导体器件编码在TCAD设备仿真中，被提议。这种图基于的通用编码方案不仅考虑材料层和设备层嵌入，还引入了一种新的空间关系嵌入，Draw inspiration from interpolation operations typically used in finite element meshing。通用物理法则从设备仿真中得到了全面的数据驱动模拟，包括代表性函数估计和电压-电流（IV）预测，基于漫步扩散模型。这两个任务都使用了一种新的图注意力网络，称为RelGAT。我们提供了全面的技术细节，以便研究者可以在设备水平采用这种人工智能驱动电子设计自动化（EDA）解决方案。
Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting
For: The paper is focused on improving the cross-domain and cross-compositional generalization of Text-to-SQL semantic parsing, which is a challenging task.* Methods: The authors propose an algorithm that performs offline sampling of a minimal set of few-shots from the training data, with complete coverage of SQL clauses, operators, and functions, and maximal domain coverage within the allowed token length. This allows for the synthesis of a fixed Generic Prompt (GP) with a diverse set of exemplars common across NL test queries, avoiding expensive test time exemplar retrieval. Additionally, the authors propose an auto-adaptation of the GP to the target database domain (DA-GP) to better handle cross-domain generalization, followed by a decomposed Least-To-Most-Prompting (LTMP-DA-GP) to handle cross-compositional generalization.* Results: The authors demonstrate superior performance on the KaggleDBQA dataset, designed to evaluate generalizability for the Text-to-SQL task. They also showcase consistent performance improvement of LTMP-DA-GP over GP, across LLMs and databases of KaggleDBQA, highlighting the efficacy and model agnostic benefits of their prompt-based adapt and decompose approach.Here’s the simplified Chinese version of the three information points:* For: 这篇论文旨在解决文本到SQLsemantic parsing中的跨领域和跨组合性泛化问题，这是一项具有挑战性的任务。* Methods: 作者们提出了一种方法，通过在训练数据集上进行Offline sampling，以获取完整的SQL子句、运算符和函数的覆盖，同时保证在允许的Token长度内具备最大的领域覆盖。这allow for the synthesis of a fixed Generic Prompt (GP) with a diverse set of exemplars common across NL test queries, avoiding expensive test time exemplar retrieval. 作者们还提出了一种自适应GP到目标数据库领域(DA-GP)，以更好地处理跨领域泛化。此外，他们还提出了一种分解的Least-To-Most-Prompting (LTMP-DA-GP)，以处理跨组合性泛化。* Results: 作者们在KaggleDBQA数据集上展现出了superior的性能，这个数据集是用于评估文本到SQL泛化性能的。他们还显示了LTMP-DA-GP在不同的LLMs和数据库上的一致性提升，这highlights the efficacy and model agnostic benefits of their prompt-based adapt and decompose approach。Abstract
Cross-domain and cross-compositional generalization of Text-to-SQL semantic parsing is a challenging task. Existing Large Language Model (LLM) based solutions rely on inference-time retrieval of few-shot exemplars from the training set to synthesize a run-time prompt for each Natural Language (NL) test query. In contrast, we devise an algorithm which performs offline sampling of a minimal set-of few-shots from the training data, with complete coverage of SQL clauses, operators and functions, and maximal domain coverage within the allowed token length. This allows for synthesis of a fixed Generic Prompt (GP), with a diverse set-of exemplars common across NL test queries, avoiding expensive test time exemplar retrieval. We further auto-adapt the GP to the target database domain (DA-GP), to better handle cross-domain generalization; followed by a decomposed Least-To-Most-Prompting (LTMP-DA-GP) to handle cross-compositional generalization. The synthesis of LTMP-DA-GP is an offline task, to be performed one-time per new database with minimal human intervention. Our approach demonstrates superior performance on the KaggleDBQA dataset, designed to evaluate generalizability for the Text-to-SQL task. We further showcase consistent performance improvement of LTMP-DA-GP over GP, across LLMs and databases of KaggleDBQA, highlighting the efficacy and model agnostic benefits of our prompt based adapt and decompose approach.
摘要
Translated into Simplified Chinese:跨Domain和跨组合性的文本到SQLsemantic parsing是一项具有挑战性的任务。现有的大型自然语言模型（LLM）基于解决方案通过推理时间获取少量示例来synthesize每个自然语言（NL）测试查询的运行时提示。相比之下，我们提出了一种算法，它在训练集上进行offline采样，收集了完整的SQL子句、运算符和函数的少量示例，并在允许的字符串长度内保证最大的Domain覆盖。这使得可以synthesize一个固定的通用提示（GP），该提示包含了NL测试查询中共享的多个示例，从而避免了Expensive的测试时间示例重新获取。我们还自动适应了GP到目标数据库Domain（DA-GP），以更好地处理跨Domain泛化。然后，我们使用了 decomposed Least-To-Most-Prompting（LTMP-DA-GP）来处理跨组合性泛化。该synthesis是一个offline任务，需要在新的数据库上进行一次性的人工 intervención。我们的方法在KaggleDBQA数据集上显示了superior的性能，KaggleDBQA数据集是用于评估文本到SQL任务的泛化性能的。我们还在LLMs和KaggleDBQA数据库之间显示了LTMP-DA-GP的性能提升，这highlights our prompt based adapt和decomposeapproach的效果和模型无关性。
A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
paper_authors: Minghao Chen, Zepeng Gao, Shuai Zhao, Qibo Qiu, Wenxiao Wang, Binbin Lin, Xiaofei He for: 本研究旨在开发一种无监督领域适应（Unsupervised Domain Adaptation，UDA）评价度量，能够无需目标验证集来评估转移模型的质量。methods: 本研究使用了基于模型预测的相互信息度量作为起点，并通过实验分析发现了三种常见问题：1）不考虑源结构；2）容易受到攻击；3）无法检测到源和目标特征的过分对应。为解决这些问题，我们在度量中添加了源精度，并使用了一个新的多层感知（MLP）分类器，在训练过程中保持不参与。此外，我们还将这种改进后的度量与数据扩展结合使用，得到了一种新的无监督UDA度量——扩展一致度量（ACM）。results: 我们通过大规模实验证明了我们提出的度量的有效性，并对前一些实验设置的缺点进行了证明。此外，我们还使用了我们提出的度量自动搜索最佳超参数集，在四种常见 benchmark 上达到了超过 manually 调参集的性能。 codes 将很快地公开。Abstract
Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set for hyper-parameter tuning and model selection. In this paper, we aim to find an evaluation metric capable of assessing the quality of a transferred model without access to target validation labels. We begin with the metric based on mutual information of the model prediction. Through empirical analysis, we identify three prevalent issues with this metric: 1) It does not account for the source structure. 2) It can be easily attacked. 3) It fails to detect negative transfer caused by the over-alignment of source and target features. To address the first two issues, we incorporate source accuracy into the metric and employ a new MLP classifier that is held out during training, significantly improving the result. To tackle the final issue, we integrate this enhanced metric with data augmentation, resulting in a novel unsupervised UDA metric called the Augmentation Consistency Metric (ACM). Additionally, we empirically demonstrate the shortcomings of previous experiment settings and conduct large-scale experiments to validate the effectiveness of our proposed metric. Furthermore, we employ our metric to automatically search for the optimal hyper-parameter set, achieving superior performance compared to manually tuned sets across four common benchmarks. Codes will be available soon.
摘要
无监督领域适应（UDA）方法可以将模型转移到目标领域无需标签。然而，这些方法需要一个标注的目标验证集来调整超参数和选择模型。在这篇论文中，我们想要找到一个可以评估转移模型的评价指标，不需要目标验证集。我们开始于基于模型预测的共同信息度的指标。通过实验分析，我们发现了三个常见的问题：1）它不考虑源结构。2）它可以轻松攻击。3）它无法探测源和目标特征的过对齐导致的负向转移。为了解决这两个问题，我们将源准确率 incorporated 到指标中，并使用一个新的多层感知（MLP）分类器，该分类器在训练时被隐藏。此外，我们还将这个提高后的指标与数据扩展结合使用，得到了一种新的无监督UDA指标——扩展一致指标（ACM）。此外，我们还对之前的实验设置进行了详细的批判，并进行了大规模的实验来验证我们的提出的指标的有效性。最后，我们使用我们的指标自动搜索最佳超参数集，在四个常见的benchmark上达到了人工调整的超参数集的超过表现。代码即将上线。
Predictive Modeling through Hyper-Bayesian Optimization
paper_authors: Manisha Senadeera, Santu Rana, Sunil Gupta, Svetha Venkatesh
for: 这 paper 是为了提高 Bayesian 优化（BO） 的模型选择效率，并且同时获取黑板函数的信息。
methods: 这 paper 使用了一种新的方法，即将模型选择和 BO integrate在一起，以达到更快的函数优化目标。这种方法通过在模型空间和函数空间之间往返，使用一个得分函数来衡量模型的质量，并将其反馈给 BO，以便更快地 convergence。
results: 这 paper 的实验结果表明，使用这种方法可以提高 BO 的样本效率，同时也可以获取黑板函数的信息。此外，这 paper 还证明了这种方法的收敛性。Abstract
Model selection is an integral problem of model based optimization techniques such as Bayesian optimization (BO). Current approaches often treat model selection as an estimation problem, to be periodically updated with observations coming from the optimization iterations. In this paper, we propose an alternative way to achieve both efficiently. Specifically, we propose a novel way of integrating model selection and BO for the single goal of reaching the function optima faster. The algorithm moves back and forth between BO in the model space and BO in the function space, where the goodness of the recommended model is captured by a score function and fed back, capturing how well the model helped convergence in the function space. The score function is derived in such a way that it neutralizes the effect of the moving nature of the BO in the function space, thus keeping the model selection problem stationary. This back and forth leads to quick convergence for both model selection and BO in the function space. In addition to improved sample efficiency, the framework outputs information about the black-box function. Convergence is proved, and experimental results show significant improvement compared to standard BO.
摘要
<>将文本翻译成简化中文。<>基于模型的优化技术，如 bayesian 优化（BO），选择模型是一个不可或缺的问题。现有方法通常将模型选择视为估计问题，在优化迭代中 periodic 更新 observations。在本文中，我们提出了一种新的方法，可以快速地达到函数的最优点。该算法在模型空间和函数空间之间往返，使用 BO 来评估模型的好坏，并将其反馈给函数空间中的 BO，以 capture 模型如何帮助函数空间中的 converges。该得分函数是设计的，以 neutralize 模型在函数空间中的移动效果，因此保持模型选择问题的静态性。这种往返机制会使 BO 在函数空间和模型空间中快速 converge。除了提高样本效率之外，该框架还输出了黑板函数的信息。 convergence 的证明和实验结果表明，与标准 BO 相比，该方法具有显著的改进。
CLAMS: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clustering
results: CLAMS可以更好地预测实际的群分化不确定性，并且与人工标注器的性能相当。此外，该研究还探讨了如何使用CLAMS来优化和benchmark数据挖掘技术。Abstract
Visual clustering is a common perceptual task in scatterplots that supports diverse analytics tasks (e.g., cluster identification). However, even with the same scatterplot, the ways of perceiving clusters (i.e., conducting visual clustering) can differ due to the differences among individuals and ambiguous cluster boundaries. Although such perceptual variability casts doubt on the reliability of data analysis based on visual clustering, we lack a systematic way to efficiently assess this variability. In this research, we study perceptual variability in conducting visual clustering, which we call Cluster Ambiguity. To this end, we introduce CLAMS, a data-driven visual quality measure for automatically predicting cluster ambiguity in monochrome scatterplots. We first conduct a qualitative study to identify key factors that affect the visual separation of clusters (e.g., proximity or size difference between clusters). Based on study findings, we deploy a regression module that estimates the human-judged separability of two clusters. Then, CLAMS predicts cluster ambiguity by analyzing the aggregated results of all pairwise separability between clusters that are generated by the module. CLAMS outperforms widely-used clustering techniques in predicting ground truth cluster ambiguity. Meanwhile, CLAMS exhibits performance on par with human annotators. We conclude our work by presenting two applications for optimizing and benchmarking data mining techniques using CLAMS. The interactive demo of CLAMS is available at clusterambiguity.dev.
摘要
<>转换给定文本到简化中文。<>可见划分是常见的感知任务在散点图中，支持多种分析任务（例如，团结标识）。然而，即使使用同一个散点图，对划分的方式（即进行可见划分）可以因个体差异和杂乱划分boundary而异。尽管如此，我们缺乏一种系统化的方法来效率地评估这种变化。在这项研究中，我们研究可见划分中的变化，我们称之为团结混淆。为此，我们引入CLAMS，一种数据驱动的视觉质量指标，用于自动预测散点图中团结的混淆程度。我们首先进行了资深研究，以确定影响可见划分的关键因素（例如，团结距离或团结大小差）。根据研究结果，我们部署了一个回归模块，以估计人类评估两个团结的可分离程度。然后，CLAMS预测团结混淆程度，通过分析所有对应的划分结果。CLAMS在预测真实团结混淆程度方面表现出色，同时与人类标注器的性能相当。我们结束我们的工作，并将两种用于优化和benchmarking数据挖掘技术的应用示例展示出来。CLAMS的交互式demo可以在clusterambiguity.dev上查看。
ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddings
results: 我们透过一个实际的应用情况来验证我们的优化方案，发现这个方案可以对扭曲度量表进行很好的优化。此外，我们还创建了一个名为ZADUVis的库，可以让用户轻松地创建扭曲度量表的可视化图示。Abstract
Dimensionality reduction (DR) techniques inherently distort the original structure of input high-dimensional data, producing imperfect low-dimensional embeddings. Diverse distortion measures have thus been proposed to evaluate the reliability of DR embeddings. However, implementing and executing distortion measures in practice has so far been time-consuming and tedious. To address this issue, we present ZADU, a Python library that provides distortion measures. ZADU is not only easy to install and execute but also enables comprehensive evaluation of DR embeddings through three key features. First, the library covers a wide range of distortion measures. Second, it automatically optimizes the execution of distortion measures, substantially reducing the running time required to execute multiple measures. Last, the library informs how individual points contribute to the overall distortions, facilitating the detailed analysis of DR embeddings. By simulating a real-world scenario of optimizing DR embeddings, we verify that our optimization scheme substantially reduces the time required to execute distortion measures. Finally, as an application of ZADU, we present another library called ZADUVis that allows users to easily create distortion visualizations that depict the extent to which each region of an embedding suffers from distortions.
摘要
Dimensionality reduction (DR) 技术自然地扭曲输入数据的原始结构，生成不完美的低维度嵌入。为了评估DR嵌入的可靠性，各种不同的扭曲度指标已经被提出。然而，在实践中实施和执行这些指标的问题仍然存在。为解决这个问题，我们介绍了ZADU，一个Python库，它提供了多种扭曲度指标，并且可以自动优化执行扭曲度指标，大幅降低执行多个指标所需的运行时间。此外，ZADU还能够详细分析DR嵌入的扭曲度，让用户了解具体的扭曲度来源。通过模拟一个实际的DR嵌入优化场景，我们证明了我们的优化方案可以减少执行扭曲度指标所需的时间。最后，作为ZADU的应用，我们介绍了ZADUVis，一个可以轻松地创建扭曲度视觉化的库，它可以详细显示嵌入中每个区域受到的扭曲度程度。
Data Collaboration Analysis applied to Compound Datasets and the Introduction of Projection data to Non-IID settings
paper_authors: Akihiro Mizoguchi, Anna Bogdanova, Akira Imakura, Tetsuya Sakurai for: 这个论文主要是研究如何使用分布式机器学习来预测化学物质的性能，以及如何在非同分布（non-IID） Setting下提高预测精度。methods: 这个研究使用了联合学习（Federated Learning）和数据合作分析（Data Collaboration Analysis）等方法来预测化学物质的性能。另外，也提出了一种基于投影数据（Projection Data）的改进方法 called Data Collaboration Analysis using Projection Data（DCPd）。results: 研究发现，在非同分布 Setting下，DCPd的机器学习性能虽然和其他方法相似，但在不同的标签偏好情况下却表现较好，而且与其他方法相比，DCPd在不同标签偏好情况下的性能差异较小。这表明，DCPd可以解决联合学习在非同分布 Setting下的低性能问题。Abstract
Given the time and expense associated with bringing a drug to market, numerous studies have been conducted to predict the properties of compounds based on their structure using machine learning. Federated learning has been applied to compound datasets to increase their prediction accuracy while safeguarding potentially proprietary information. However, federated learning is encumbered by low accuracy in not identically and independently distributed (non-IID) settings, i.e., data partitioning has a large label bias, and is considered unsuitable for compound datasets, which tend to have large label bias. To address this limitation, we utilized an alternative method of distributed machine learning to chemical compound data from open sources, called data collaboration analysis (DC). We also proposed data collaboration analysis using projection data (DCPd), which is an improved method that utilizes auxiliary PubChem data. This improves the quality of individual user-side data transformations for the projection data for the creation of intermediate representations. The classification accuracy, i.e., area under the curve in the receiver operating characteristic curve (ROC-AUC) and AUC in the precision-recall curve (PR-AUC), of federated averaging (FedAvg), DC, and DCPd was compared for five compound datasets. We determined that the machine learning performance for non-IID settings was in the order of DCPd, DC, and FedAvg, although they were almost the same in identically and independently distributed (IID) settings. Moreover, the results showed that compared to other methods, DCPd exhibited a negligible decline in classification accuracy in experiments with different degrees of label bias. Thus, DCPd can address the low performance in non-IID settings, which is one of the challenges of federated learning.
摘要
因为带药到市场的时间和成本很高，许多研究都是使用机器学习预测药物性质基于其结构。 federated learning 已经应用于药物数据集来提高预测精度，但是在非标一致（non-IID）设置下，其精度低。为了解决这些 limitation，我们使用了一种名为数据合作分析（DC）的 alternativemethod of distributed machine learning to chemical compound data from open sources。我们还提出了基于投影数据（DCPd）的改进方法，该方法使用auxiliary PubChem数据来提高个人用户 сторо面数据变换的质量。我们对五个药物数据集进行了 federated averaging（FedAvg）、DC 和 DCPd 的比较，发现在非标一致设置下，DCPd 的机器学习性能高于 DC 和 FedAvg，尽管在标一致设置下它们几乎相同。此外，结果表明，相比其他方法，DCPd 在不同的标签偏好度下 exhibited 微不足的下降。因此，DCPd 可以解决 federated learning 在非标一致设置下的低性能问题。
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
results: 实验结果表明，该方法可以有效地提高PU学习的精度和稳定性，并且可以在各种学习任务上实现良好的效果。Abstract
Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the unlabeled data using ad-hoc thresholds so that conventional supervised methods can be applied with both positive and negative samples. Owing to the label uncertainty among the unlabeled data, errors of misclassifying unlabeled positive samples as negative samples inevitably appear and may even accumulate during the training processes. Those errors often lead to performance degradation and model instability. To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first. Similar intuition has been utilized in curriculum learning to only use easier cases in the early stage of training before introducing more complex cases. Specifically, we utilize a novel ``hardness'' measure to distinguish unlabeled samples with a high chance of being negative from unlabeled samples with large label noise. An iterative training strategy is then implemented to fine-tune the selection of negative samples during the training process in an iterative manner to include more ``easy'' samples in the early stage of training. Extensive experimental validations over a wide range of learning tasks show that this approach can effectively improve the accuracy and stability of learning with positive and unlabeled data. Our code is available at https://github.com/woriazzc/Robust-PU
摘要
学习正面和无标签数据的方法，称为正面无标签（PU）学习，在最近几年内吸引了很多关注。一种常见的PU学习方法是从无标签数据中随机选择一些假负样本，使得传统的监督学习方法可以使用正面和负样本。由于无标签数据中的标签不确定，在训练过程中会出现错误地将无标签正样本标记为负样本的现象，这可能会在训练过程中积累。这些错误会导致性能下降和模型不稳定。为了减轻标签不确定性的影响和提高学习正面和无标签数据的稳定性，我们提出了一种新的稳定PU学习方法。我们使用了一种新的“困难度”度量，以分辨无标签样本中高概率是负样本的和大量标签噪音。然后，我们实现了一种迭代训练策略，在训练过程中多次精度地选择负样本，以包括更多的“易于学习”的样本在早期训练阶段。我们对各种学习任务进行了广泛的实验 validate，结果表明，这种方法可以有效地提高学习正面和无标签数据的精度和稳定性。我们的代码可以在https://github.com/woriazzc/Robust-PU中找到。
Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction
results: 对比于传统的DR评估方法（如可靠性和连续性，库拉布-莱布尔差异），Label-T&C表现更高的准确性，并且可扩展到大规模数据集。此外，本文还提供了一些实践案例，用于揭示DR技术和其超参数的内在特性。Abstract
A common way to evaluate the reliability of dimensionality reduction (DR) embeddings is to quantify how well labeled classes form compact, mutually separated clusters in the embeddings. This approach is based on the assumption that the classes stay as clear clusters in the original high-dimensional space. However, in reality, this assumption can be violated; a single class can be fragmented into multiple separated clusters, and multiple classes can be merged into a single cluster. We thus cannot always assure the credibility of the evaluation using class labels. In this paper, we introduce two novel quality measures -- Label-Trustworthiness and Label-Continuity (Label-T&C) -- advancing the process of DR evaluation based on class labels. Instead of assuming that classes are well-clustered in the original space, Label-T&C work by (1) estimating the extent to which classes form clusters in the original and embedded spaces and (2) evaluating the difference between the two. A quantitative evaluation showed that Label-T&C outperform widely used DR evaluation measures (e.g., Trustworthiness and Continuity, Kullback-Leibler divergence) in terms of the accuracy in assessing how well DR embeddings preserve the cluster structure, and are also scalable. Moreover, we present case studies demonstrating that Label-T&C can be successfully used for revealing the intrinsic characteristics of DR techniques and their hyperparameters.
摘要
一种常见的维度减少（DR） embedding 评估方法是通过衡量 labels 是否形成紧凑、相互隔离的群集来评估 embedding 的可靠性。这种方法假设高维空间中的类具有清晰的分布，但在实际情况下，这种假设可能被违反；一个类可能会被分割成多个分立的群集，多个类可能会被合并为一个群集。因此，我们无法一直保证评估使用类标签的可靠性。在这篇论文中，我们引入了两种新的质量指标：Label-Trustworthiness 和 Label-Continuity（Label-T&C），这些指标旨在基于类标签来评估维度减少 embedding 的可靠性。不同于假设高维空间中的类具有清晰的分布，Label-T&C 通过（1）估计原始和嵌入空间中类的群集程度，（2）评估这两个空间之间的差异来评估维度减少 embedding 的可靠性。一个量化评估表明，Label-T&C 在评估维度减少 embedding 保持类群结构的准确性方面表现出色，并且可扩展性也高。此外，我们还提供了用 Label-T&C 评估维度减少技术和其超参数的实际案例研究。
Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
results: 我们的实验结果表明，我们所提出的神经网络模型在许多方面比其他模型（包括 SOTA Siamese Autoencoder 方法）perform 更好，并且可以更好地泛化和更快速地训练。Abstract
Learning distance functions between complex objects, such as the Wasserstein distance to compare point sets, is a common goal in machine learning applications. However, functions on such complex objects (e.g., point sets and graphs) are often required to be invariant to a wide variety of group actions e.g. permutation or rigid transformation. Therefore, continuous and symmetric product functions (such as distance functions) on such complex objects must also be invariant to the product of such group actions. We call these functions symmetric and factor-wise group invariant (or SFGI functions in short). In this paper, we first present a general neural network architecture for approximating SFGI functions. The main contribution of this paper combines this general neural network with a sketching idea to develop a specific and efficient neural network which can approximate the $p$-th Wasserstein distance between point sets. Very importantly, the required model complexity is independent of the sizes of input point sets. On the theoretical front, to the best of our knowledge, this is the first result showing that there exists a neural network with the capacity to approximate Wasserstein distance with bounded model complexity. Our work provides an interesting integration of sketching ideas for geometric problems with universal approximation of symmetric functions. On the empirical front, we present a range of results showing that our newly proposed neural network architecture performs comparatively or better than other models (including a SOTA Siamese Autoencoder based approach). In particular, our neural network generalizes significantly better and trains much faster than the SOTA Siamese AE. Finally, this line of investigation could be useful in exploring effective neural network design for solving a broad range of geometric optimization problems (e.g., $k$-means in a metric space).
摘要
学习 Complex 对象之间的距离函数，如 Wasserstein 距离比较点集，是机器学习应用中常见的目标。然而，函数在这些复杂对象上（例如点集和图）经常需要对广泛的群作用（例如 permutation 或扭转变换）进行抗变换。因此，在这些复杂对象上的连续和共轭产品函数（如距离函数）必须对群作用的乘积进行抗变换。我们称这类函数为共轭和因子化群作用抗变换函数（SFGI 函数）。在这篇论文中，我们首先提出一种通用的神经网络架构，用于近似 SFGI 函数。我们的主要贡献是将这种通用神经网络与抽象思想结合，开发了特定和高效的神经网络，用于近似 $p$-th Wasserstein 距离 between 点集。非常重要的是，模型复杂度不依赖输入点集的大小。在理论上，我们的结果表明，存在一种能够近似 Wasserstein 距离的神经网络，并且其模型复杂度受到输入点集的大小的限制。我们的工作提供了对几何问题的解决方案的有趣的整合，以及通用神经网络的近似Symmetric 函数的能力。在实际方面，我们发现我们的新提出的神经网络架构在多个实际问题中表现较好，比如 SOTA Siamese Autoencoder 基于方法。具体来说，我们的神经网络在泛化和训练速度方面表现较好，而且可以在训练时更好地控制模型的复杂度。最后，这种研究方向可能会对解决广泛的几何优化问题（例如 metric 空间中的 $k$-means）提供有用的思路。
results: 我们的最佳模型在三个dataset（CMU-MOSI、CMU-MOSEI和CH-SIMS）上达到了状态之arte性能，并在大多数指标中超越其他方法。我们发现，训练在多模态特征上可以提高单模态测试性能，而根据数据集注释schema设计融合方法可以提高模型性能。这些结果提供了优化特征选择和融合方法的路线图，以提高情感识别 neural network 性能。Abstract
In this work we investigate the optimal selection and fusion of features across multiple modalities and combine these in a neural network to improve emotion detection. We compare different fusion methods and examine the impact of multi-loss training within the multi-modality fusion network, identifying useful findings relating to subnet performance. Our best model achieves state-of-the-art performance for three datasets (CMU-MOSI, CMU-MOSEI and CH-SIMS), and outperforms the other methods in most metrics. We have found that training on multimodal features improves single modality testing and designing fusion methods based on dataset annotation schema enhances model performance. These results suggest a roadmap towards an optimized feature selection and fusion approach for enhancing emotion detection in neural networks.
摘要
在这项研究中，我们调查了不同Modalities之间的最佳选择和融合方法，并将这些方法 integrate into a neural network 以提高情感识别。我们比较了不同的融合方法，并查看了在多模态融合网络中多loss训练的影响，发现有用的发现关于子网络性能。我们的最佳模型在CMU-MOSI、CMU-MOSEI和CH-SIMS三个 datasets 上达到了状态机器的性能，并在大多数指标中超过其他方法。我们发现，在多模态特征上进行训练可以提高单模态测试，而基于dataset annotation schema的融合方法设计可以提高模型性能。这些结果提供了增强情感识别在神经网络中的优化特征选择和融合方法的路线图。
Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation
methods: 使用量化通信 schemes 和 shared “hidden” state 技术
results: 提供了理论上的 convergence guarantees 和实验 validate Results on 标准 benchmark 上Abstract
Asynchronous Federated Learning with Buffered Aggregation (FedBuff) is a state-of-the-art algorithm known for its efficiency and high scalability. However, it has a high communication cost, which has not been examined with quantized communications. To tackle this problem, we present a new algorithm (QAFeL), with a quantization scheme that establishes a shared "hidden" state between the server and clients to avoid the error propagation caused by direct quantization. This approach allows for high precision while significantly reducing the data transmitted during client-server interactions. We provide theoretical convergence guarantees for QAFeL and corroborate our analysis with experiments on a standard benchmark.
摘要
“异步联合学习（FedBuff）”是当前最佳实践，具有高效率和可扩展性。然而，它具有高通信成本，这未曾与量化通信相关研究。为解决这个问题，我们提出了一个新算法（QAFeL），具有量化方案，在服务器和客户端之间共享一个“隐藏”状态，以避免因直接量化而导致的错误协议。这种方法允许高精度，同时减少了在客户端-服务器交互中传输的数据量。我们提供了论证性的收敛保证，并在标准 benchmark 上进行了实验 validate。
AQUILA: Communication Efficient Federated Learning with Adaptive Quantization of Lazily-Aggregated Gradients
results: 在非同一样式的分布式学习 Setting中，AQUILA 可以大幅减少通信成本，同时保持模型性能的相似性，并且可以适应不同的设备和数据偏差。Abstract
The widespread adoption of Federated Learning (FL), a privacy-preserving distributed learning methodology, has been impeded by the challenge of high communication overheads, typically arising from the transmission of large-scale models. Existing adaptive quantization methods, designed to mitigate these overheads, operate under the impractical assumption of uniform device participation in every training round. Additionally, these methods are limited in their adaptability due to the necessity of manual quantization level selection and often overlook biases inherent in local devices' data, thereby affecting the robustness of the global model. In response, this paper introduces AQUILA (adaptive quantization of lazily-aggregated gradients), a novel adaptive framework devised to effectively handle these issues, enhancing the efficiency and robustness of FL. AQUILA integrates a sophisticated device selection method that prioritizes the quality and usefulness of device updates. Utilizing the exact global model stored by devices, it enables a more precise device selection criterion, reduces model deviation, and limits the need for hyperparameter adjustments. Furthermore, AQUILA presents an innovative quantization criterion, optimized to improve communication efficiency while assuring model convergence. Our experiments demonstrate that AQUILA significantly decreases communication costs compared to existing methods, while maintaining comparable model performance across diverse non-homogeneous FL settings, such as Non-IID data and heterogeneous model architectures.
摘要
通用学习（FL）的广泛采用受到了大规模模型的传输 overhead 的挑战。现有的 adaptive quantization 方法可以减少这些 overhead，但是它们假设所有训练轮都有 uniform 的设备参与，并且它们的适应性受限，因为需要手动选择 quantization 级别。此外，这些方法通常会忽略本地设备数据中的偏见，从而影响全局模型的稳定性。为此，这篇论文提出了 AQUILA（适应量化 Lazy 梯度），一种新的适应性框架，可以有效地解决这些问题，提高 FL 的效率和稳定性。AQUILA integrates 一种智能的设备选择方法，根据设备更新的质量和用用性来优先选择设备。通过使用设备上存储的准确全球模型，AQUILA 可以更准确地选择设备，降低模型偏差，并减少 hyperparameter 调整的需求。此外，AQUILA 还提出了一种优化的量化标准，可以提高通信效率，保证模型收敛。我们的实验表明，AQUILA 比现有方法更有效地减少通信成本，同时保持非常多样化的 FL 设定下的模型性能相对一致。
Best-Subset Selection in Generalized Linear Models: A Fast and Consistent Algorithm via Splicing Technique
results: 根据实验结果，这个方法可以在高维度情况下更好地选择最佳子集，并且比较快速，相比之下glmnet和ncvreg等工具kit更快。Abstract
In high-dimensional generalized linear models, it is crucial to identify a sparse model that adequately accounts for response variation. Although the best subset section has been widely regarded as the Holy Grail of problems of this type, achieving either computational efficiency or statistical guarantees is challenging. In this article, we intend to surmount this obstacle by utilizing a fast algorithm to select the best subset with high certainty. We proposed and illustrated an algorithm for best subset recovery in regularity conditions. Under mild conditions, the computational complexity of our algorithm scales polynomially with sample size and dimension. In addition to demonstrating the statistical properties of our method, extensive numerical experiments reveal that it outperforms existing methods for variable selection and coefficient estimation. The runtime analysis shows that our implementation achieves approximately a fourfold speedup compared to popular variable selection toolkits like glmnet and ncvreg.
摘要
高维度泛化线性模型中，必须确定一个稀畴模型，以便准确地考虑响应的变化。虽然最佳子集问题被广泛认为是这类问题的圣杯，但是实现计算效率或统计保证是困难的。在这篇文章中，我们想要通过使用快速的算法来选择最佳子集，以确保高度的确定性。我们提出了一种算法来实现最佳子集恢复，并在正则条件下进行了推广。对于样本大小和维度，我们的算法的计算复杂度随样本大小和维度的幂次方式增长。除了证明我们的方法的统计性质外，我们还进行了广泛的数值实验，发现我们的方法可以在变量选择和系数估计方面超越现有的方法。我们的实现的运行时间分析表明，我们的实现可以相比popular变量选择工具包如glmnet和ncvreg achieve approximately fourfold speedup.
EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learning
results: 实验结果显示，提出的方法可以达到强劲的结果，并且超过了传统的单阶段完全监睹学习。此外，文章还进行了细化和敏感性研究，以评估不同方法的影响。这篇研究对情感计算和认知负担领域的发展做出了贡献，并开启了新的跨领域转移学习和自我监睹预训练的研究途径。Abstract
Cognitive load, the amount of mental effort required for task completion, plays an important role in performance and decision-making outcomes, making its classification and analysis essential in various sensitive domains. In this paper, we present a new solution for the classification of cognitive load using electroencephalogram (EEG). Our model uses a transformer architecture employing transfer learning between emotions and cognitive load. We pre-train our model using self-supervised masked autoencoding on emotion-related EEG datasets and use transfer learning with both frozen weights and fine-tuning to perform downstream cognitive load classification. To evaluate our method, we carry out a series of experiments utilizing two publicly available EEG-based emotion datasets, namely SEED and SEED-IV, for pre-training, while we use the CL-Drive dataset for downstream cognitive load classification. The results of our experiments show that our proposed approach achieves strong results and outperforms conventional single-stage fully supervised learning. Moreover, we perform detailed ablation and sensitivity studies to evaluate the impact of different aspects of our proposed solution. This research contributes to the growing body of literature in affective computing with a focus on cognitive load, and opens up new avenues for future research in the field of cross-domain transfer learning using self-supervised pre-training.
摘要
“认知负担”，指的是完成任务所需的心理努力量，在完成任务和做出决策时扮演着重要的角色。因此，认知负担的分类和分析在各种敏感领域都是非常重要的。在这篇论文中，我们提出了一个新的认知负担分类方法，使用电enzephalogram（EEG）。我们的模型使用transformer架构，通过将情感和认知负担之间的学习整合在一起。我们在这个模型中使用了自我监督隐藏式复原，并使用两种方法：冻结重量和精确地复原，进行下游认知负担分类。为了评估我们的方法，我们在两个公开 disponibile EEG基于情感 datasets，namely SEED和SEED-IV，进行预训练，而下游认知负担分类则使用CL-Drive dataset。实验结果显示，我们的提出方法具有强大的表现和超越传统单阶充足学习。此外，我们还进行了细节抑制和敏感性研究，以评估不同方面的影响。这些研究将对情感 computing的发展做出贡献，并开启了跨领域批量学习使用自我监督隐藏式预训练的新领域。
Beam Detection Based on Machine Learning Algorithms
for: precisely determine the positions of free electron laser beams on screens
methods: sequence of machine learning models, including transfer training in a self-constructed convolutional neural network based on VGG16 model and support vector regression model
results: 85.8% correct prediction on test dataAbstract
The positions of free electron laser beams on screens are precisely determined by a sequence of machine learning models. Transfer training is conducted in a self-constructed convolutional neural network based on VGG16 model. Output of intermediate layers are passed as features to a support vector regression model. With this sequence, 85.8% correct prediction is achieved on test data.
摘要
文本中的自由电子激光束在屏幕上的位置精确地由一个机器学习模式序列确定。在自己构建的卷积神经网络基于VGG16模型中进行了传输训练。输出的中间层的输出被用作特征传递到支持向量回归模型。通过这个序列，在测试数据上达到了85.8%的正确预测率。Note: The translation is in Simplified Chinese, which is the standard form of Chinese used in mainland China and Singapore. If you need Traditional Chinese, please let me know.
ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworks
results: 研究表明，使用LLMs可以在物理科学中实现高精度的结构材料预测和生成，并且可以帮助找到新的结构材料和应用。同时，研究也揭示了使用LLMs的一些缺点和限制。Abstract
ChatMOF is an autonomous Artificial Intelligence (AI) system that is built to predict and generate of metal-organic frameworks (MOFs). By leveraging a large-scale language model (gpt-3.5-turbo), ChatMOF extracts key details from textual inputs and delivers appropriate responses, thus eliminating the necessity for rigid structured queries. The system is comprised of three core components (i.e. an agent, a toolkit, and an evaluator) and it forms a robust pipeline that manages a variety of tasks, including data retrieval, property prediction, and structure generation. The study further explores the merits and constraints of using large language models (LLMs) AI system in material sciences using and showcases its transformative potential for future advancements.
摘要
chatMOF 是一个无人驾驶的人工智能系统（AI），用于预测和生成金属有机框架（MOFs）。通过充分利用大规模语言模型（gpt-3.5-turbo），chatMOF 从文本输入中提取重要资讯，并提供适当的回应，因此消除了僵化的结构化查询的需要。系统由三个核心 ком成分（即代理人、工具组和评估器）组成，形成一个完整的管道，处理许多任务，包括数据检索、属性预测和结构生成。研究进一步探讨使用大语言模型（LLMs）AI系统在材料科学中的优点和缺点，并展示其将来发展的transformative潜力。
Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks
results: 在复杂的感知 datasets 上，通过实现现有的不确定性估计算算法，证明了 capsa 框架可以轻松地组合不同类型的风险量化算法，并提供了全面的风险意识。Abstract
The modern pervasiveness of large-scale deep neural networks (NNs) is driven by their extraordinary performance on complex problems but is also plagued by their sudden, unexpected, and often catastrophic failures, particularly on challenging scenarios. Existing algorithms that provide risk-awareness to NNs are complex and ad-hoc. Specifically, these methods require significant engineering changes, are often developed only for particular settings, and are not easily composable. Here we present capsa, a framework for extending models with risk-awareness. Capsa provides a methodology for quantifying multiple forms of risk and composing different algorithms together to quantify different risk metrics in parallel. We validate capsa by implementing state-of-the-art uncertainty estimation algorithms within the capsa framework and benchmarking them on complex perception datasets. We demonstrate capsa's ability to easily compose aleatoric uncertainty, epistemic uncertainty, and bias estimation together in a single procedure, and show how this approach provides a comprehensive awareness of NN risk.
摘要
现代大规模深度神经网络（NN）的广泛应用受其在复杂问题上的非凡表现驱动，但同时也受到其意外、不可预期的失败的威胁，尤其是在复杂的场景下。现有的风险意识提供方法都是复杂且尝试性的，需要大量的工程改进，通常只适用于特定的场景，并且不易组合。我们提出了capsa框架，用于扩展模型的风险意识。capsa提供了多种风险量化的方法ology，可以并行量化不同的风险指标。我们通过在capsa框架中实现现状风险估计算法，并对复杂的感知数据集进行了 benchmarking，以示capsa的能力可以轻松地组合不同的风险估计算法，并提供全面的NN风险意识。
Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
results: 研究发现，经过 instruciton 调教的模型具有更多的偏见，尤其是 Flan-T5、GPT3.5 和 GPT4 等模型。这些偏见在人类决策和理解中都有表现。Abstract
Recent studies show that instruction tuning and learning from human feedback improve the abilities of large language models (LMs) dramatically. While these tuning methods can make models generate high-quality text, we conjecture that more implicit cognitive biases may arise in these fine-tuned models. Our work provides evidence that these fine-tuned models exhibit biases that were absent or less pronounced in their pretrained predecessors. We examine the extent of this phenomenon in three cognitive biases - the decoy effect, the certainty effect, and the belief bias - all of which are known to influence human decision-making and reasoning. Our findings highlight the presence of these biases in various models, especially those that have undergone instruction tuning, such as Flan-T5, GPT3.5, and GPT4. This research constitutes a step toward comprehending cognitive biases in instruction-tuned LMs, which is crucial for the development of more reliable and unbiased language models.
摘要
latest studies show that instruction tuning and learning from human feedback can significantly improve the abilities of large language models (LMs). while these tuning methods can make models generate high-quality text, we speculate that more implicit cognitive biases may arise in these fine-tuned models. our work provides evidence that these fine-tuned models exhibit biases that were absent or less pronounced in their pretrained predecessors. we examine the extent of this phenomenon in three cognitive biases - the decoy effect, the certainty effect, and the belief bias - all of which are known to influence human decision-making and reasoning. our findings highlight the presence of these biases in various models, especially those that have undergone instruction tuning, such as Flan-T5, GPT3.5, and GPT4. this research constitutes a step toward comprehending cognitive biases in instruction-tuned LMs, which is crucial for the development of more reliable and unbiased language models.
Deep Reinforcement Learning-Based Battery Conditioning Hierarchical V2G Coordination for Multi-Stakeholder Benefits
paper_authors: Yubao Zhang, Xin Chen, Yi Gu, Zhicheng Li, Wu Kai
for: 提高可再生能源利用率和电网稳定性，适用于大规模EV充电 scheduling 策略
methods: 基于深度遗产 reinforcement learning 和 Proof of Stake 算法，实现多方利益协调
results: 相比四种基准方案，多方协调策略可以提高可再生能源消耗率、缓和负荷波动、满足EV充电商需求，降低充电成本和电池质量下降Abstract
With the growing prevalence of electric vehicles (EVs) and advancements in EV electronics, vehicle-to-grid (V2G) techniques and large-scale scheduling strategies have emerged to promote renewable energy utilization and power grid stability. This study proposes a multi-stakeholder hierarchical V2G coordination based on deep reinforcement learning (DRL) and the Proof of Stake algorithm. Furthermore, the multi-stakeholders include the power grid, EV aggregators (EVAs), and users, and the proposed strategy can achieve multi-stakeholder benefits. On the grid side, load fluctuations and renewable energy consumption are considered, while on the EVA side, energy constraints and charging costs are considered. The three critical battery conditioning parameters of battery SOX are considered on the user side, including state of charge, state of power, and state of health. Compared with four typical baselines, the multi-stakeholder hierarchical coordination strategy can enhance renewable energy consumption, mitigate load fluctuations, meet the energy demands of EVA, and reduce charging costs and battery degradation under realistic operating conditions.
摘要
On the grid side, the approach takes into account load fluctuations and renewable energy consumption, while on the EVA side, it considers energy constraints and charging costs. For users, the approach considers three critical battery conditioning parameters: state of charge, state of power, and state of health.Compared to four typical baselines, the multi-stakeholder hierarchical coordination strategy can enhance renewable energy consumption, mitigate load fluctuations, meet the energy demands of EVA, and reduce charging costs and battery degradation under realistic operating conditions.
Robust Single-view Cone-beam X-ray Pose Estimation with Neural Tuned Tomography (NeTT) and Masked Neural Radiance Fields (mNeRF)
paper_authors: Chaochao Zhou, Syed Hasib Akhter Faruqui, Abhinav Patel, Ramez N. Abdalla, Michael C. Hurley, Ali Shaibani, Matthew B. Potts, Babak S. Jahromi, Leon Cho, Sameer A. Ansari, Donald R. Cantrell
results: 这篇论文提出了两种新的高精度视图合成方法，即Neural Tuned Tomography（NeTT）和masked Neural Radiance Fields（mNeRF）。这两种方法都基于经典的扁球计算机断层成像（CBCT），NeTT直接优化CBCT的密度，而mNeRF的非零值是通过3D掩模来约束。这两种方法都能够提高pose estimation的准确率，并且NeTT的计算成本远低于mNeRF。此外，这篇论文还证明了NeTT可以在训练和pose estimation阶段具有更好的一致性，并且可以在不同的主体上进行高精度的DRR Synthesized和pose estimation。因此，这篇论文建议使用NeTT来实现 robust pose estimation。Abstract
Many tasks performed in image-guided, mini-invasive, medical procedures can be cast as pose estimation problems, where an X-ray projection is utilized to reach a target in 3D space. Expanding on recent advances in the differentiable rendering of optically reflective materials, we introduce new methods for pose estimation of radiolucent objects using X-ray projections, and we demonstrate the critical role of optimal view synthesis in performing this task. We first develop an algorithm (DiffDRR) that efficiently computes Digitally Reconstructed Radiographs (DRRs) and leverages automatic differentiation within TensorFlow. Pose estimation is performed by iterative gradient descent using a loss function that quantifies the similarity of the DRR synthesized from a randomly initialized pose and the true fluoroscopic image at the target pose. We propose two novel methods for high-fidelity view synthesis, Neural Tuned Tomography (NeTT) and masked Neural Radiance Fields (mNeRF). Both methods rely on classic Cone-Beam Computerized Tomography (CBCT); NeTT directly optimizes the CBCT densities, while the non-zero values of mNeRF are constrained by a 3D mask of the anatomic region segmented from CBCT. We demonstrate that both NeTT and mNeRF distinctly improve pose estimation within our framework. By defining a successful pose estimate to be a 3D angle error of less than 3 deg, we find that NeTT and mNeRF can achieve similar results, both with overall success rates more than 93%. However, the computational cost of NeTT is significantly lower than mNeRF in both training and pose estimation. Furthermore, we show that a NeTT trained for a single subject can generalize to synthesize high-fidelity DRRs and ensure robust pose estimations for all other subjects. Therefore, we suggest that NeTT is an attractive option for robust pose estimation using fluoroscopic projections.
摘要
许多在图像指导、微创性医疗过程中进行的任务可以被视为定位估计问题，其中使用X射线投影来到达3D空间中的目标。在这篇文章中，我们推出了一种新的定位估计方法，使用X射线投影来估计透明物体的定位。我们首先开发了一种效率高的计算Digitally Reconstructed Radiographs（DRR）的算法（DiffDRR），并利用TensorFlow中的自动导数来实现。在这种方法中，我们使用一个定制的损失函数来衡量DRR从Random Initialized Pose（RIP）中synthesized的和真实的fluoroscopic图像之间的相似性。我们还提出了两种高精度视图合成方法：Neural Tuned Tomography（NeTT）和Masked Neural Radiance Fields（mNeRF）。两种方法都基于经典的射线计算电脑断层Tomography（CBCT）；NeTT直接优化CBCT的密度，而mNeRF的非零值是由3Dmask的Anatomic Region（AR）段化from CBCT进行限制。我们发现NeTT和mNeRF都可以大幅提高定位估计的精度，并且NeTT的计算成本远低于mNeRF。此外，我们发现一个NeTT在单个主体上进行Training可以为所有其他主体synthesize高品质的DRR和确保Robust定位估计。因此，我们建议NeTT作为Robust定位估计的可靠选择。
SkullGAN: Synthetic Skull CT Generation with Generative Adversarial Networks
paper_authors: Kasra Naftchi-Ardebili, Karanpartap Singh, Reza Pourabolghasem, Pejman Ghanouni, Gerald R. Popelka, Kim Butts Pauly
for: 这个研究想要使用生成器进行人类头骨的数据生成，以便将机器学习技术应用到医疗领域中。
methods: 这个研究使用了生成对抗网络（GAN），将 CT 图像转换为生成的人类头骨图像。
results: 研究发现，SkullGAN 生成的人类头骨图像与实际的头骨图像之间存在类似的三个量化医学特征，并且通过应用 SkullGAN 检测器来类别，发现 SkullGAN 生成的头骨图像集和实际头骨图像集之间是无法区分的。Abstract
Deep learning offers potential for various healthcare applications involving the human skull but requires extensive datasets of curated medical images. To overcome this challenge, we propose SkullGAN, a generative adversarial network (GAN), to create large datasets of synthetic skull CT slices, reducing reliance on real images and accelerating the integration of machine learning into healthcare. In our method, CT slices of 38 subjects were fed to SkullGAN, a neural network comprising over 200 million parameters. The synthetic skull images generated were evaluated based on three quantitative radiological features: skull density ratio (SDR), mean thickness, and mean intensity. They were further analyzed using t-distributed stochastic neighbor embedding (t-SNE) and by applying the SkullGAN discriminator as a classifier. The results showed that SkullGAN-generated images demonstrated similar key quantitative radiological features to real skulls. Further definitive analysis was undertaken by applying the discriminator of SkullGAN, where the SkullGAN discriminator classified 56.5% of a test set of real skull images and 55.9% of the SkullGAN-generated images as reals (the theoretical optimum being 50%), demonstrating that the SkullGAN-generated skull set is indistinguishable from the real skull set - within the limits of our nonlinear classifier. Therefore, SkullGAN makes it possible to generate large numbers of synthetic skull CT segments, necessary for training neural networks for medical applications involving the human skull. This mitigates challenges associated with preparing large, high-quality training datasets, such as access, capital, time, and the need for domain expertise.
摘要
深度学习对医疗领域中人骨的应用具有潜在优势，但是它需要大量高质量医疗图像数据集来进行训练。为了解决这个挑战，我们提议了一种基于生成对抗网络（GAN）的方法，称之为SkullGAN。SkullGAN可以生成大量的人工骨CT切片，从而减少对真实图像的依赖，并促进机器学习在医疗领域的整合。我们的方法是将38名参与者的CT切片传输给SkullGAN，这是一个包含超过2亿个参数的神经网络。SkullGAN生成的人工骨图像被评估基于三个量化医学特征：骨密度比率（SDR）、平均厚度和平均亮度。它们还被使用t-分布随机 neigh embedding（t-SNE）分析，并通过应用SkullGAN推论器来分类。结果表明，SkullGAN生成的图像与真实骨头图像之间存在相似的三个量化医学特征。进一步的定论分析表明，SkullGAN推论器可以将56.5%的测试集真实骨头图像和55.9%的SkullGAN生成图像分类为真实图像（理论最佳值为50%），这表明SkullGAN生成的骨头集与真实骨头集是可区分的，至少在我们的非线性分类器的限度内。因此，SkullGAN可以生成大量的人工骨CT切片，这些切片可以用于训练医学应用中需要骨头图像的神经网络。这种方法可以解决准备大量高质量医疗图像数据集的挑战，包括访问、资本、时间和域专业知识的需求。
CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
results: 我们在两个物体分类 dataset 上进行了评估，并取得了当前最佳表现（SOTA）的结果。此外，我们还在一个机器人上进行了增量学习和不断学习的测试，并证明了机器人可以在有限的人工协助下，不断学习分类大量的家用品。Abstract
For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification datasets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.
摘要
For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification datasets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot, demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.Here's the translation in Traditional Chinese as well:For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification datasets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot, demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.
paper_authors: Boah Kim, Yujin Oh, Bradford J. Wood, Ronald M. Summers, Jong Chul Ye
for: This paper aims to develop a self-supervised vessel segmentation method for medical imaging, which can help improve the accuracy and efficiency of vascular disease diagnosis and interventional planning.
methods: The proposed method, called C-DARL, combines a diffusion module and a generation module to learn the distribution of multi-domain blood vessel data, and employs contrastive learning through a mask-based contrastive loss to improve the realism of vessel representations.
results: Experimental results on various vessel datasets show that C-DARL achieves performance improvement over baseline methods with noise robustness, demonstrating the effectiveness of the proposed method for vessel segmentation in medical imaging.Here’s the summary in Traditional Chinese:
results: 实验结果显示，C-DARL在不同的血管数据集上实现了基准方法的性能改进，并具有噪声抗性，证明了提案的方法的有效性。Abstract
Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.
摘要
血管分割在医疗成像中是一项非常重要的步骤，用于诊断血管疾病和静脉介入规划，在各种临床场景中具有广泛的应用前景。然而，手动标注血管mask是一项困难和耗时的任务，因为血管分支和结构较为复杂。为了解决这个问题，本文提出了一种自我超级视图的血管分割方法，即对比扩散对抗表示学习（C-DARL）模型。我们的模型由扩散模块和生成模块组成，通过生成多域血管数据的分布来学习血管图像的分布。此外，我们采用了对比学习，通过一个面积基于的对比损失函数，使模型学习更真实的血管表示。为验证效果，C-DARL被训练使用了多种血管数据集，包括肠动脉摄影、腹部数字抽象摄影和视网膜成像。实验结果表明，我们的模型在噪音Robustness下达到了基eline方法的性能提升，这表明C-DARL是一种有效的血管分割方法。
results: 实验结果表明，这种优化方法可以快速地收敛到最优解，并且可以从任何初始点开始，无需进行任何参数调整。Abstract
Majorization-minimization (MM) is a family of optimization methods that iteratively reduce a loss by minimizing a locally-tight upper bound, called a majorizer. Traditionally, majorizers were derived by hand, and MM was only applicable to a small number of well-studied problems. We present optimizers that instead derive majorizers automatically, using a recent generalization of Taylor mode automatic differentiation. These universal MM optimizers can be applied to arbitrary problems and converge from any starting point, with no hyperparameter tuning.
摘要
大量化抑制（MM）是一家优化方法的家族，通过迭代地减少损失函数，最小化一个本地紧急上限函数，称为主要函数。在过去，主要函数通常是通过手动计算得到的，因此MM只能应用于一小部分已经广泛研究的问题上。我们提出了一种使用最近的欧拉积分自动微分的一般化方法来自动生成主要函数。这些普适的MM优化器可以应用于任何问题，并从任何初始点开始，无需参数调整。
Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?
paper_authors: Ari Holtzman, Peter West, Luke Zettlemoyer
for: 本研究目的是解释语音模型如何完成多种任务，并且帮助未来的研究。
methods: 本研究使用系统性的方法来分解语音模型的行为，以解释它们在不同任务中的表现。
results: 本研究获得了一系列的结果，包括语音模型在不同任务中的表现，以及它们的行为可以被分解为不同的类别。Abstract
Coaxing out desired behavior from pretrained models, while avoiding undesirable ones, has redefined NLP and is reshaping how we interact with computers. What was once a scientific engineering discipline-in which building blocks are stacked one on top of the other-is arguably already a complex systems science, in which emergent behaviors are sought out to support previously unimagined use cases. Despite the ever increasing number of benchmarks that measure task performance, we lack explanations of what behaviors language models exhibit that allow them to complete these tasks in the first place. We argue for a systematic effort to decompose language model behavior into categories that explain cross-task performance, to guide mechanistic explanations and help future-proof analytic research.
摘要
使预训练模型展现愿景行为，而不是不良行为，已经重新定义了自然语言处理（NLP），并在我们与计算机之间的交互方式中造成了改变。过去，建筑块一个在另一个之上排序的科学工程 discipline，现在可能已经变成了复杂系统科学，寻找emergent行为以支持前未想象的用 случа。尽管任务性能的测试benchmark数量不断增加，但我们仍然缺乏任务完成所需行为的解释。我们提出了一种系统性的努力，即将语言模型行为分类为可以解释跨任务性能的类别，以导引机械性解释和未来研究。
Attribution-Scores in Data Management and Explainable Machine Learning
results: 论文提出了一种量化度量数据库的一致性，并提供了高效计算 Shap-score 的方法。Abstract
We describe recent research on the use of actual causality in the definition of responsibility scores as explanations for query answers in databases, and for outcomes from classification models in machine learning. In the case of databases, useful connections with database repairs are illustrated and exploited. Repairs are also used to give a quantitative measure of the consistency of a database. For classification models, the responsibility score is properly extended and illustrated. The efficient computation of Shap-score is also analyzed and discussed. The emphasis is placed on work done by the author and collaborators.
摘要
我们描述了最近的研究，把实际 causality 引入责任分数的定义中，以解释查询结果在数据库中的解释，以及机器学习模型中的结果的出现。在数据库中，我们利用了有用的连接，并使用了修复来给出数据库的数量化度量。对于机器学习模型，我们正确地扩展了责任分数，并用修复来衡量模型的一致性。我们还分析了efficiently computation Shap-score的问题。我们强调了作者和合作者的工作。Note: "实际 causality" in the original text is translated as "实际 causality" in Simplified Chinese, which is a literal translation. However, "实际 causality" is not a commonly used term in Simplified Chinese, and a more appropriate translation might be "真实 causality" (zhēnshí causality) or "实际效果" (shíjì efect).
General Anomaly Detection of Underwater Gliders Validated by Large-scale Deployment Dataset
results: 研究发现，使用异常检测算法可以帮助飞行器驾驶员在实时监控异常情况，避免更大的损害。Abstract
This paper employs an anomaly detection algorithm to assess the normal operation of underwater gliders in unpredictable ocean environments. Real-time alerts can be provided to glider pilots upon detecting any anomalies, enabling them to assume control of the glider and prevent further harm. The detection algorithm is applied to abundant data sets collected in real glider deployments led by the Skidaway Institute of Oceanography (SkIO) and the University of South Florida (USF). Regarding generality, the experimental evaluation is composed of both offline and online detection modes. The offline detection utilizes full post-recovery data sets, which carries high-resolution information, to present detailed analysis of the anomaly and compare it with pilot logs. The online detection focuses on the real-time subsets of data transmitted from the glider at the surfacing events. While the real-time data may not contain as much rich information as the post-recovery data, the online detection is of great importance as it allows glider pilots to monitor potential abnormal conditions in real time.
摘要
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
results: 研究发现，预训练模型可以在有大量无标记数据的情况下Soundly exceed GBDTs（和其他非预训练模型）的性能，并且在评分异常数据时也可以获得 significatively better robustness。Abstract
While deep learning (DL) models are state-of-the-art in text and image domains, they have not yet consistently outperformed Gradient Boosted Decision Trees (GBDTs) on tabular Learning-To-Rank (LTR) problems. Most of the recent performance gains attained by DL models in text and image tasks have used unsupervised pretraining, which exploits orders of magnitude more unlabeled data than labeled data. To the best of our knowledge, unsupervised pretraining has not been applied to the LTR problem, which often produces vast amounts of unlabeled data. In this work, we study whether unsupervised pretraining can improve LTR performance over GBDTs and other non-pretrained models. Using simple design choices--including SimCLR-Rank, our ranking-specific modification of SimCLR (an unsupervised pretraining method for images)--we produce pretrained deep learning models that soundly outperform GBDTs (and other non-pretrained models) in the case where labeled data is vastly outnumbered by unlabeled data. We also show that pretrained models also often achieve significantly better robustness than non-pretrained models (GBDTs or DL models) in ranking outlier data.
摘要
Translated into Simplified Chinese:while deep learning (DL) 模型在文本和图像领域是现状最佳，但它们尚未一直保持GBDTs在标量学习到rank（LTR）问题上的表现。大多数最近在文本和图像任务中获得的性能提升都是通过无监督预训练来实现，这种方法可以利用数个数量级的无标签数据。据我们所知，无监督预训练没有被应用于LTR问题，这个问题通常会生成巨量的无标签数据。在这项工作中，我们研究了无监督预训练是否可以提高LTR性能，并与其他非预训练模型相比。我们采用了简单的设计选择，包括我们的排名特有的SimCLR-Rank修改版（一种图像无监督预训练方法）。我们生成了预训练深度学习模型，这些模型在标量数据充足时与GBDTs和其他非预训练模型相比，具有更好的表现。我们还表明了预训练模型在排名异常数据时的更好的Robustness。
paper_authors: Hussain Ahmad Madni, Rao Muhammad Umer, Gian Luca Foresti
for: This paper aims to address the challenges of data and model heterogeneity in Federated Learning (FL) by exploiting both heterogeneities simultaneously.
methods: The proposed method, MDH-FL, uses knowledge distillation and a symmetric loss to minimize the impact of heterogeneity on the model performance.
results: The experimental results on medical datasets demonstrate the superiority of the proposed approach over existing methods.Abstract
Federated Learning (FL) is an evolving machine learning method in which multiple clients participate in collaborative learning without sharing their data with each other and the central server. In real-world applications such as hospitals and industries, FL counters the challenges of data heterogeneity and model heterogeneity as an inevitable part of the collaborative training. More specifically, different organizations, such as hospitals, have their own private data and customized models for local training. To the best of our knowledge, the existing methods do not effectively address both problems of model heterogeneity and data heterogeneity in FL. In this paper, we exploit the data and model heterogeneity simultaneously, and propose a method, MDH-FL (Exploiting Model and Data Heterogeneity in FL) to solve such problems to enhance the efficiency of the global model in FL. We use knowledge distillation and a symmetric loss to minimize the heterogeneity and its impact on the model performance. Knowledge distillation is used to solve the problem of model heterogeneity, and symmetric loss tackles with the data and label heterogeneity. We evaluate our method on the medical datasets to conform the real-world scenario of hospitals, and compare with the existing methods. The experimental results demonstrate the superiority of the proposed approach over the other existing methods.
摘要
federated learning (FL) 是一种发展中的机器学习方法，在多个客户端参与协同学习而无需分享数据之间和中央服务器。在实际应用中，如医院和产业中，FL 对数据不同和模型不同的问题作出了有效应对。具体来说，不同的组织，如医院，拥有自己的私有数据和本地训练的自定义模型。据我们所知，现有的方法未能有效地解决 FL 中的数据不同和模型不同问题。在这篇论文中，我们利用数据不同和模型不同的特点，并提出了一种方法，即 MDH-FL（利用数据和模型不同的特点进行 FL），以解决这些问题，从而提高 FL 的效率。我们使用知识传承和对称损失来减少不同和其影响于模型性能。知识传承用于解决模型不同问题，而对称损失则用于解决数据和标签不同问题。我们在医疗数据集上进行了实验，以验证这种方法在实际应用中的可行性，并与现有方法进行比较。实验结果表明，我们提出的方法在模型性能方面表现出优于现有方法。
DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification
results: 实验结果显示，DiffusAL 方法在多种 benchmark 数据集上具有显著的弹性和可转移性，并在 100% 的数据集和标签预算下具有优于随机选择的表现。Abstract
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative subset of nodes that maximizes label efficiency. However, deciding which heuristic is best suited for an unlabeled graph to increase label efficiency is a persistent challenge. Existing solutions either neglect aligning the learned model and the sampling method or focus only on limited selection aspects. They are thus sometimes worse or only equally good as random sampling. In this work, we introduce a novel active graph learning approach called DiffusAL, showing significant robustness in diverse settings. Toward better transferability between different graph structures, we combine three independent scoring functions to identify the most informative node samples for labeling in a parameter-free way: i) Model Uncertainty, ii) Diversity Component, and iii) Node Importance computed via graph diffusion heuristics. Most of our calculations for acquisition and training can be pre-processed, making DiffusAL more efficient compared to approaches combining diverse selection criteria and similarly fast as simpler heuristics. Our experiments on various benchmark datasets show that, unlike previous methods, our approach significantly outperforms random selection in 100% of all datasets and labeling budgets tested.
摘要 translate-language: zh-CNNode 分类是 attributed graphs 的核心任务，但是成功的图学习解决方案需要具有足够的标注数据。为了降低标注成本，活动图学习专注于选择最有价值的节点子集，以提高标签效率。然而，选择没有标注的图中最有价值的节点是一个持续的挑战。现有的解决方案可能会忽略将学习模型和采样方法相匹配，或者只专注于有限的选择方面。这些方法在某些情况下可能比随机采样更差，或者只是与随机采样相等。在这种情况下，我们介绍了一种新的活动图学习方法，称为DiffusAL，它在多种场景中表现出了显著的鲁棒性。为了更好地传递不同的图结构之间，我们将三种独立的分数函数结合起来，以选择最有用的节点样本进行标签：i) 模型不确定性，ii) 多样性分数，和 iii) 图diffusion 的节点重要性。大多数我们的收购和训练计算可以预处理，使得DiffusAL比 combine 多种选择 criterion 和类似快速的方法更高效。我们在多种 bench marks 上进行的实验表明，与先前的方法不同，我们的方法在 100% 的所有数据集和标注预算上都能够明显超过随机选择。
Formally Explaining Neural Networks within Reactive Systems
results: 研究人员在两个popular的自动导航 benchmark上评估了这种技术，并观察到它可以高效地计算出最小和最小的解释，比之前的状态对技术更高效。此外，研究人员还证明了这种技术生成的正式解释比非验证基于的XAI技术更可靠。Abstract
Deep neural networks (DNNs) are increasingly being used as controllers in reactive systems. However, DNNs are highly opaque, which renders it difficult to explain and justify their actions. To mitigate this issue, there has been a surge of interest in explainable AI (XAI) techniques, capable of pinpointing the input features that caused the DNN to act as it did. Existing XAI techniques typically face two limitations: (i) they are heuristic, and do not provide formal guarantees that the explanations are correct; and (ii) they often apply to ``one-shot'' systems, where the DNN is invoked independently of past invocations, as opposed to reactive systems. Here, we begin bridging this gap, and propose a formal DNN-verification-based XAI technique for reasoning about multi-step, reactive systems. We suggest methods for efficiently calculating succinct explanations, by exploiting the system's transition constraints in order to curtail the search space explored by the underlying verifier. We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art. We also demonstrate that our methods produce formal explanations that are more reliable than competing, non-verification-based XAI techniques.
摘要
In this paper, we propose a formal DNN-verification-based XAI technique for reasoning about multi-step, reactive systems. Our approach leverages the system's transition constraints to efficiently calculate succinct explanations, reducing the search space explored by the underlying verifier. We evaluate our method on two popular benchmarks from the domain of automated navigation and show that our approach can efficiently compute minimal and minimum explanations, significantly outperforming the state of the art. We also demonstrate that our methods produce formal explanations that are more reliable than competing, non-verification-based XAI techniques.我们在这篇文章中提出了一种基于 Deep Neural Networks (DNNs) 的可解释 AI (XAI) 技术，用于理解和解释 DNNs 在反应系统中的行为。然而，现有的 XAI 技术存在两个限制：首先，它们通常是有规则的，无法提供正式的 garantía 正确性;其次，它们通常适用于 "一击" 系统，在 DNN 独立于过去邀请时被邀请的情况下进行调用，而不是反应系统。在这篇文章中，我们开始bridging这个差距，并提出了一种基于 DNN 验证的可解释技术，用于理解多步、反应系统。我们提出了一种利用系统的转换约束来减少搜索空间的方法，以便高效计算简短的解释。我们在两个流行的自动导航 benchmark 上测试了我们的方法，并观察到我们的方法可以高效计算最小和最小的解释，明显超越当前的状态。我们还表明了我们的方法生成的正式解释比竞争对手的非验证基于 XAI 技术更可靠。
Semi-Supervised Laplacian Learning on Stiefel Manifolds
results: compared to 最新的state-of-the-art和传统 semi-supervised learning 方法，我们的框架在低、中、高标签率下 achieve lower classification error。Abstract
Motivated by the need to address the degeneracy of canonical Laplace learning algorithms in low label rates, we propose to reformulate graph-based semi-supervised learning as a nonconvex generalization of a \emph{Trust-Region Subproblem} (TRS). This reformulation is motivated by the well-posedness of Laplacian eigenvectors in the limit of infinite unlabeled data. To solve this problem, we first show that a first-order condition implies the solution of a manifold alignment problem and that solutions to the classical \emph{Orthogonal Procrustes} problem can be used to efficiently find good classifiers that are amenable to further refinement. Next, we address the criticality of selecting supervised samples at low-label rates. We characterize informative samples with a novel measure of centrality derived from the principal eigenvectors of a certain submatrix of the graph Laplacian. We demonstrate that our framework achieves lower classification error compared to recent state-of-the-art and classical semi-supervised learning methods at extremely low, medium, and high label rates. Our code is available on github\footnote{anonymized for submission}.
摘要
<>将文本翻译成简化中文。<>受到低标签率下 Laplace 学习算法的异常性的启发，我们提议将图像基于 semi-supervised learning 重新定义为非 conjugate 矩阵的一种通用化问题。这种重定义是基于 Laplacian 域的均值偏 Parameters 的一种限制，它在无穷多个无标签数据的极限下具有一定的坚定性。为解决这个问题，我们首先证明在某种特定的 manifold alignment 问题中，第一个ORDER condition 的解是一个 manifold alignment 问题的解，并且可以使用经典的 orthogonal procrustes 问题来高效地找到可以进一步精细化的好的分类器。接下来，我们讨论在低标签率下选择supervised 样本的关键性。我们提出一种新的中心性度量，基于图 Laplacian 矩阵的特定子矩阵的主要特征值。我们证明，我们的框架在低、中和高标签率下具有更低的分类错误率，比之前的最新状态艺术和经典 semi-supervised learning 方法。我们的代码可以在 GitHub 上找到（注释除去）。
A Suite of Fairness Datasets for Tabular Classification
results: 期望这些函数可以促进未来的公正性意识Machine learning研究中的实验评估Here’s a breakdown of each point:
for: The paper is written for improving the fairness of machine-learning classifiers for tabular data.
methods: The paper introduces a suite of functions for fetching 20 fairness datasets and providing associated fairness metadata, which can be used for more rigorous experimental evaluations in future fairness-aware machine learning research.
results: The paper hopes that these functions can promote more rigorous experimental evaluations in future fairness-aware machine learning research.Abstract
There have been many papers with algorithms for improving fairness of machine-learning classifiers for tabular data. Unfortunately, most use only very few datasets for their experimental evaluation. We introduce a suite of functions for fetching 20 fairness datasets and providing associated fairness metadata. Hopefully, these will lead to more rigorous experimental evaluations in future fairness-aware machine learning research.
摘要
“有很多论文提出了对机器学习分类器的公平性进行改善的算法。却是，大多数使用的数据集只有几个。我们介绍了一个函数套件，可以获取20个公平性数据集和相关的公平性元件。希望这些函数能够带来未来公平性意识机器学习研究的更加严谨的实验评估。”Here's the breakdown of the translation:“有很多论文” (有很多论文) - There have been many papers“提出了对机器学习分类器的公平性进行改善的算法” (提出了对机器学习分类器的公平性进行改善的算法) - There have been many papers with algorithms for improving the fairness of machine learning classifiers“却是” (却是) - Unfortunately“大多数使用的数据集只有几个” (大多数使用的数据集只有几个) - Most use only a few datasets for their experimental evaluation“我们介绍了一个函数套件” (我们介绍了一个函数套件) - We introduce a suite of functions“可以获取20个公平性数据集和相关的公平性元件” (可以获取20个公平性数据集和相关的公平性元件) - That can fetch 20 fairness datasets and provide associated fairness metadata“希望这些函数能够带来未来公平性意识机器学习研究的更加严谨的实验评估” (希望这些函数能够带来未来公平性意识机器学习研究的更加严谨的实验评估) - Hopefully, these functions can lead to more rigorous experimental evaluations in future fairness-aware machine learning research.
Ensemble Learning with Residual Transformer for Brain Tumor Segmentation
methods: 本研究提出了一种新的网络架构，即将 Transformers integrated into a self-adaptive U-Net，以利用 Transformers 的内置注意机制和像素级标注来捕捉3D精度volume context。此外，我们还添加了 residual connection 来避免信息流失传递，并 explore ensemble methods 来利用不同模型在不同情况下的优势。
results: 在 BraTS 2021 dataset（3D）上，我们的模型实现了87.6%的 mean Dice score，超越了现有的状态 Elluminate 方法，说明可以通过组合多种架构来优化脑肿瘤分 segmentation。Abstract
Brain tumor segmentation is an active research area due to the difficulty in delineating highly complex shaped and textured tumors as well as the failure of the commonly used U-Net architectures. The combination of different neural architectures is among the mainstream research recently, particularly the combination of U-Net with Transformers because of their innate attention mechanism and pixel-wise labeling. Different from previous efforts, this paper proposes a novel network architecture that integrates Transformers into a self-adaptive U-Net to draw out 3D volumetric contexts with reasonable computational costs. We further add a residual connection to prevent degradation in information flow and explore ensemble methods, as the evaluated models have edges on different cases and sub-regions. On the BraTS 2021 dataset (3D), our model achieves 87.6% mean Dice score and outperforms the state-of-the-art methods, demonstrating the potential for combining multiple architectures to optimize brain tumor segmentation.
摘要
brain tumor segmentation 是一个活跃的研究领域，因为复杂形态和文本化肿瘤难以定界，以及通用的 U-Net 架构失败。最近，各种神经网络架构的组合在主流研究中，特别是 U-Net 与 Transformers 的组合，因为它们的自然注意机制和像素级标注。与前一些尝试不同，这篇论文提出了一种新的网络架构，将 Transformers integrate into a self-adaptive U-Net，以获取3D积体上的合理计算成本下的Context。此外，我们还添加了保持信息流不减的径迹连接，并 explore ensemble 方法，因为评估模型在不同的情况和子区域上有着优势。在 BraTS 2021 数据集（3D）上，我们的模型达到了87.6%的平均 dice 分数，超越了现有的方法，这表明将多种架构组合起来优化脑肿瘤分 segmentation 的潜力。
DiviML: A Module-based Heuristic for Mapping Neural Networks onto Heterogeneous Platforms
paper_authors: Yassine Ghannane, Mohamed S. Abdelfattah for:* The paper is written to address the challenge of optimizing deep neural network (DNN) execution on heterogeneous datacenter hardware, specifically considering both data and model parallelism.methods:* The paper proposes a compiler-level partitioning approach that leverages mixed integer linear programming (MILP) and a modularity-based heuristic to automatically partition and device map DNNs onto multiple interconnected hardware devices.results:* The proposed framework can achieve more than 3 times lower latency and up to 2.9 times higher throughput compared to naively running DNNs on the fastest GPU, while maintaining solution quality. The modularity-based “splitting” heuristic improves solution runtime up to 395 times without sacrificing solution quality, and outperforms all other heuristics by 30-60% solution quality.Here is the information in Simplified Chinese:for:* 本文是为了解决现代数据中心硬件多样化的挑战，具体是考虑数据并行和模型并行。methods:* 本文提出了一种编译级别的分配方法，利用混合整数线性规划（MILP）和一种模块性基于规则的启发函数来自动将深度神经网络（DNNs）分配到多个连接的硬件设备上。results:* 提posed的框架可以比直接在最快的GPU上运行DNNs更低的延迟和更高的吞吐量，同时保持解决方案质量。 modularity-based “splitting”启发函数可以提高解决时间Up to 395倍，而无需明显牺牲解决方案质量，并在其他启发函数中出现30-60%的解决质量。Abstract
Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we develop an approach for compiler-level partitioning of deep neural networks (DNNs) onto multiple interconnected hardware devices. We present a general framework for heterogeneous DNN compilation, offering automatic partitioning and device mapping. Our scheduler integrates both an exact solver, through a mixed integer linear programming (MILP) formulation, and a modularity-based heuristic for scalability. Furthermore, we propose a theoretical lower bound formula for the optimal solution, which enables the assessment of the heuristic solutions' quality. We evaluate our scheduler in optimizing both conventional DNNs and randomly-wired neural networks, subject to latency and throughput constraints, on a heterogeneous system comprised of a CPU and two distinct GPUs. Compared to na\"ively running DNNs on the fastest GPU, he proposed framework can achieve more than 3$\times$ times lower latency and up to 2.9$\times$ higher throughput by automatically leveraging both data and model parallelism to deploy DNNs on our sample heterogeneous server node. Moreover, our modularity-based "splitting" heuristic improves the solution runtime up to 395$\times$ without noticeably sacrificing solution quality compared to an exact MILP solution, and outperforms all other heuristics by 30-60% solution quality. Finally, our case study shows how we can extend our framework to schedule large language models across multiple heterogeneous servers by exploiting symmetry in the hardware setup. Our code can be easily plugged in to existing frameworks, and is available at https://github.com/abdelfattah-lab/diviml.
摘要
现代数据中心越来越多样化，包括专门的网络硬件、视频处理硬件和深度学习硬件。为了利用现代数据中心的多样化计算能力，我们开发了一种编译器层 partitioning 技术，将深度神经网络（DNNs）分配到多个连接的硬件设备上。我们提出了一个通用的多型 DNN 编译框架，包括自动分配和设备映射。我们的调度器结合了精确的整数线性Programming（MILP）方法和模块性基于的优化器，以确保可扩展性。此外，我们还提出了一个优化目标函数的下界公式，以评估优化解的质量。我们在一个包括 CPU 和两个不同 GPU 的多型系统上测试了我们的调度器，并证明了与直接在最快 GPU 上运行 DNNs 相比，我们的框架可以实现更低的延迟和更高的吞吐量，通过自动利用数据并模型并行性来部署 DNNs。此外，我们的模块性基于的"拆分"优化器可以提高解 runtime 至多 395 倍，而不是明显降低解质量。最后，我们的案例研究显示了如何使用 symmetry 在硬件设置上将大语言模型分布到多个多样化服务器上。我们的代码可以轻松地插入到现有框架中，并可以在 上获取。
Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects
results: 该论文使用COB-3D-v2数据集进行训练，并通过比较其他状态艺法的表现，表明F-CON可以在实际世界中提供更好的卷积排序性能。此外，该论文还在实际世界中 equip 了一个爬行机器人，并在受排序的复杂对象中进行了实际应用。Abstract
Dense packing in pick-and-place systems is an important feature in many warehouse and logistics applications. Prior work in this space has largely focused on planning algorithms in simulation, but real-world packing performance is often bottlenecked by the difficulty of perceiving 3D object geometry in highly occluded, partially observed scenes. In this work, we present a fully-convolutional shape completion model, F-CON, which can be easily combined with off-the-shelf planning methods for dense packing in the real world. We also release a simulated dataset, COB-3D-v2, that can be used to train shape completion models for real-word robotics applications, and use it to demonstrate that F-CON outperforms other state-of-the-art shape completion methods. Finally, we equip a real-world pick-and-place system with F-CON, and demonstrate dense packing of complex, unseen objects in cluttered scenes. Across multiple planning methods, F-CON enables substantially better dense packing than other shape completion methods.
摘要
密集填充在选择和放置系统中是非常重要的特性，在仓储和物流应用中具有广泛的应用。过去的工作主要集中在仿真中进行规划算法，但在实际情况中，填充性能frequently被 occluded, partially observed scene的3D объек的geometry perceiving difficulty所 bottleneck。在这项工作中，我们提出了一种可以与市场上 readily available planning方法结合的fully-convolutional shape completion模型，F-CON，可以在实际世界中提高填充性能。我们还发布了COB-3D-v2仿真数据集，可以用于训练shape completion模型，并在这个数据集上证明F-CON超过了其他状态对shape completion方法。最后，我们将实际世界中的选择和放置系统设备F-CON，并在拥挤的场景中 dense packing复杂、未看过的物体。在不同的规划方法下，F-CON实现了较好的密集填充性能。
New Lower Bounds for Testing Monotonicity and Log Concavity of Distributions
paper_authors: Yuqian Cheng, Daniel M. Kane, Zhicheng Zheng
for: 这 paper 用于证明分布测试下界 bound 的新技术。
methods: 该技术使用 pair of moment-matching families of distributions，通过修改每个分布的概率值，使一个家keep 定义不等式，而另一个家violate 它们。
results: 该技术可以获得新的下界 bound для monotonicity testing over discrete cubes，以及 tight lower bounds для log-concavity testing。Abstract
We develop a new technique for proving distribution testing lower bounds for properties defined by inequalities involving the bin probabilities of the distribution in question. Using this technique we obtain new lower bounds for monotonicity testing over discrete cubes and tight lower bounds for log-concavity testing. Our basic technique involves constructing a pair of moment-matching families of distributions by tweaking the probabilities of pairs of bins so that one family maintains the defining inequalities while the other violates them.
摘要
我们开发了一种新的技术，用于证明分布测试下界 для由不等式定义的性质。使用这种技术，我们得到了新的下界 для monotonicity testing over discrete cubes，以及紧靠的下界 для log-concavity testing。我们的基本技术是构造一对具有相同幂次的两个分布家族，其中一家具有定义不等式的条件，而另一家则违反这些不等式。通过这种方式，我们可以比较这两个分布家族的分布特征，从而证明分布测试的下界。
A Novel Deep Learning based Model to Defend Network Intrusion Detection System against Adversarial Attacks
results: 本研究结果分为三个阶段：1）之前敌意攻击，2）之后敌意攻击，3）之后对抗训练。使用了加拿大网络安全检测系统2017年版（CICIDS-2017）数据集进行评估，并使用了多种性能指标如f1-score、准确率等进行评估。Abstract
Network Intrusion Detection System (NIDS) is an essential tool in securing cyberspace from a variety of security risks and unknown cyberattacks. A number of solutions have been implemented for Machine Learning (ML), and Deep Learning (DL) based NIDS. However, all these solutions are vulnerable to adversarial attacks, in which the malicious actor tries to evade or fool the model by injecting adversarial perturbed examples into the system. The main aim of this research work is to study powerful adversarial attack algorithms and their defence method on DL-based NIDS. Fast Gradient Sign Method (FGSM), Jacobian Saliency Map Attack (JSMA), Projected Gradient Descent (PGD) and Carlini & Wagner (C&W) are four powerful adversarial attack methods implemented against the NIDS. As a defence method, Adversarial Training is used to increase the robustness of the NIDS model. The results are summarized in three phases, i.e., 1) before the adversarial attack, 2) after the adversarial attack, and 3) after the adversarial defence. The Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CICIDS-2017) dataset is used for evaluation purposes with various performance measurements like f1-score, accuracy etc.
摘要
网络侵入检测系统（NIDS）是保护网络安全的重要工具，它可以检测到多种安全风险和未知的网络攻击。为了提高NIDS的检测精度，许多解决方案已经被应用于机器学习（ML）和深度学习（DL）基于的NIDS。然而，这些解决方案都受到了对抗攻击的威胁，其中恶意攻击者会尝试通过投入对抗扰动的例子来欺骗模型。本研究的主要目标是研究对DL-based NIDS的强大对抗攻击算法和防御策略。本研究使用了FGSM、JSMA、PGD和C&W等四种强大对抗攻击方法，并使用了对抗训练来提高NIDS模型的可靠性。Results are summarized in three phases: before the adversarial attack, after the adversarial attack, and after the adversarial defense.用于评估的数据集是CICIDS-2017。Results are evaluated using various performance metrics such as f1-score and accuracy.
Crowd Safety Manager: Towards Data-Driven Active Decision Support for Planning and Control of Crowd Events
results: 该论文的结果表明，使用Resono数据源，可以在多天前为事件规划提供多日预测。XGBoost框架在对比其他机器学习技术时表现出最高的准确性。结果表明，预测的准确性足够高，但certain locations may benefit from additional input data to further enhance prediction quality。Abstract
This paper presents novel technology and methodology aimed at enhancing crowd management in both the planning and operational phases. The approach encompasses innovative data collection techniques, data integration, and visualization using a 3D Digital Twin, along with the incorporation of artificial intelligence (AI) tools for risk identification. The paper introduces the Bowtie model, a comprehensive framework designed to assess and predict risk levels. The model combines objective estimations and predictions, such as traffic flow operations and crowdedness levels, with various aggravating factors like weather conditions, sentiments, and the purpose of visitors, to evaluate the expected risk of incidents. The proposed framework is applied to the Crowd Safety Manager project in Scheveningen, where the DigiTwin is developed based on a wealth of real-time data sources. One noteworthy data source is Resono, offering insights into the number of visitors and their movements, leveraging a mobile phone panel of over 2 million users in the Netherlands. Particular attention is given to the left-hand side of the Bowtie, which includes state estimation, prediction, and forecasting. Notably, the focus is on generating multi-day ahead forecasts for event-planning purposes using Resono data. Advanced machine learning techniques, including the XGBoost framework, are compared, with XGBoost demonstrating the most accurate forecasts. The results indicate that the predictions are adequately accurate. However, certain locations may benefit from additional input data to further enhance prediction quality. Despite these limitations, this work contributes to a more effective crowd management system and opens avenues for further advancements in this critical field.
摘要
The proposed framework is applied to the Crowd Safety Manager project in Scheveningen, where the DigiTwin is developed based on a wealth of real-time data sources. One notable data source is Resono, which provides insights into the number of visitors and their movements, leveraging a mobile phone panel of over 2 million users in the Netherlands. The focus is on generating multi-day ahead forecasts for event planning purposes using Resono data, and advanced machine learning techniques, including the XGBoost framework, are compared. The results indicate that the predictions are adequately accurate, but certain locations may benefit from additional input data to further enhance prediction quality.Overall, this work contributes to a more effective crowd management system and opens up new avenues for further advancements in this critical field.
Using Kernel SHAP XAI Method to optimize the Network Anomaly Detection Model
results: 本论文的实验结果显示，使用kernelSHAP方法可以提高网络异常检测模型的精度、回传率、精度和F分数。将这种方法应用于网络侦错探测可以增加模型的准确性和可靠性。Abstract
Anomaly detection and its explanation is important in many research areas such as intrusion detection, fraud detection, unknown attack detection in network traffic and logs. It is challenging to identify the cause or explanation of why one instance is an anomaly? and the other is not due to its unbounded and lack of supervisory nature. The answer to this question is possible with the emerging technique of explainable artificial intelligence (XAI). XAI provides tools and techniques to interpret and explain the output and working of complex models such as Deep Learning (DL). This paper aims to detect and explain network anomalies with XAI, kernelSHAP method. The same approach is used to improve the network anomaly detection model in terms of accuracy, recall, precision and f score. The experiment is conduced with the latest CICIDS2017 dataset. Two models are created (Model_1 and OPT_Model) and compared. The overall accuracy and F score of OPT_Model (when trained in unsupervised way) are 0.90 and 0.76, respectively.
摘要
“异常检测和其解释在许多研究领域都是重要的，如侵入检测、诈骗检测、未知攻击检测在网络流量和日志中。但是确定一个实例是异常的原因，而另一个不是，是一个挑战。这个问题的答案可能通过新兴的解释人工智能（XAI）技术得到解决。XAI提供了解释和解释复杂模型，如深度学习（DL）的工具和技术。这篇论文旨在使用XAI技术检测和解释网络异常，并使用kernelSHAP方法进行改进。实验使用最新的CICIDS2017 dataset，创建了两个模型（Model_1和OPT_Model），并对它们进行比较。OPT_Model在无监督的情况下训练时的总准确率和F分数分别为0.90和0.76。”Note that the translation is in Simplified Chinese, which is the standard writing system used in mainland China. If you need Traditional Chinese, please let me know and I can provide that as well.
T-Fusion Net: A Novel Deep Neural Network Augmented with Multiple Localizations based Spatial Attention Mechanisms for Covid-19 Detection
results: 对 Covid-19 (SARS-CoV-2 CT scan) 数据集进行实验，提出的 T-Fusion Net 和 homogeneous ensemble 模型均显示出比其他状态对照方法更好的性能，准确率分别达到 97.59% 和 98.4%。Abstract
In recent years, deep neural networks are yielding better performance in image classification tasks. However, the increasing complexity of datasets and the demand for improved performance necessitate the exploration of innovative techniques. The present work proposes a new deep neural network (called as, T-Fusion Net) that augments multiple localizations based spatial attention. This attention mechanism allows the network to focus on relevant image regions, improving its discriminative power. A homogeneous ensemble of the said network is further used to enhance image classification accuracy. For ensembling, the proposed approach considers multiple instances of individual T-Fusion Net. The model incorporates fuzzy max fusion to merge the outputs of individual nets. The fusion process is optimized through a carefully chosen parameter to strike a balance on the contributions of the individual models. Experimental evaluations on benchmark Covid-19 (SARS-CoV-2 CT scan) dataset demonstrate the effectiveness of the proposed T-Fusion Net as well as its ensemble. The proposed T-Fusion Net and the homogeneous ensemble model exhibit better performance, as compared to other state-of-the-art methods, achieving accuracy of 97.59% and 98.4%, respectively.
摘要
现在的深度神经网络在图像分类任务中表现更好，但是随着数据集的增加和性能的需求，需要探索新的技术。本文提出了一种新的深度神经网络（称为T-Fusion Net），它在多个本地化位置基于的空间注意力 Mechanism 中加入了多个本地化位置的注意力机制，使网络能够更好地关注相关的图像区域，提高其分类力。然后，这个网络的多个实例被用来提高图像分类精度。为了整合，该方法考虑多个个体T-Fusion Net的拟合。这个模型使用了最大值拟合来融合各个网络的输出。拟合过程中选择了一个精心选择的参数，以达到各个模型的贡献平衡。实验表明，提案的T-Fusion Net和多个实例模型在 Covid-19（SARS-CoV-2 CT 扫描）数据集上表现出色，其中T-Fusion Net的准确率为97.59%，多个实例模型的准确率为98.4%。
Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
results: 论文结束时未提出具体的结果，但认为这个领域具有很大的潜力和挑战。Abstract
Generative Artificial Intelligence (AI) is one of the most exciting developments in Computer Science of the last decade. At the same time, Reinforcement Learning (RL) has emerged as a very successful paradigm for a variety of machine learning tasks. In this survey, we discuss the state of the art, opportunities and open research questions in applying RL to generative AI. In particular, we will discuss three types of applications, namely, RL as an alternative way for generation without specified objectives; as a way for generating outputs while concurrently maximizing an objective function; and, finally, as a way of embedding desired characteristics, which cannot be easily captured by means of an objective function, into the generative process. We conclude the survey with an in-depth discussion of the opportunities and challenges in this fascinating emerging area.
摘要
优化人工智能（AI）是过去十年计算机科学中最吸引人的发展之一。同时，对称学习（RL）已成为许多机器学习任务中非常成功的方法论。在这篇评论中，我们讨论了在应用RL到生成AI方面的状态、机遇和开放的研究问题。具体来说，我们将讨论以下三种应用：RL作为不具体目标的生成方式；RL作为同时最大化目标函数的生成输出方式；RL作为插入感知不易被目标函数捕捉的特点的生成过程中的方法。我们在这篇评论结束时对这个吸引人的新兴领域的机会和挑战进行了深入的讨论。
paper_authors: Anastasios N. Angelopoulos, Emmanuel J. Candes, Ryan J. Tibshirani
for: 这 paper 的目的是提供一种方便使用的时间序列预测方法，并提供正式的保证。
methods: 这 paper 使用了充分采用了抗干扰预测、控制理论和在线预测等方法，能够适应系统性错误的存在。
results: 实验表明，这 paper 的方法可以在美国州际 COVID-19 死亡人数的4个星期前预测中提供更好的覆盖率，以及在电能需求、股票市场收益和气温等领域的预测中达到更高的准确率。Abstract
We study the problem of uncertainty quantification for time series prediction, with the goal of providing easy-to-use algorithms with formal guarantees. The algorithms we present build upon ideas from conformal prediction and control theory, are able to prospectively model conformal scores in an online setting, and adapt to the presence of systematic errors due to seasonality, trends, and general distribution shifts. Our theory both simplifies and strengthens existing analyses in online conformal prediction. Experiments on 4-week-ahead forecasting of statewide COVID-19 death counts in the U.S. show an improvement in coverage over the ensemble forecaster used in official CDC communications. We also run experiments on predicting electricity demand, market returns, and temperature using autoregressive, Theta, Prophet, and Transformer models. We provide an extendable codebase for testing our methods and for the integration of new algorithms, data sets, and forecasting rules.
摘要
我们研究了时间序列预测不确定性评估的问题，目的是提供有正式保证的易用算法。我们的算法基于协形预测和控制理论的想法，可在线设置 prospectively 模型协形分数，并适应系统性错误的季节性、趋势和总分布变化。我们的理论简化并强化了现有的在线协形预测分析。我们在美国州际 COVID-19 死亡人数预测4个礼拜前进行了实验，比 Ensemble 预测器使用在官方CDC通信中的表现更好。我们还在预测电能需求、股票市场收益和温度上使用拟合、Theta、Prophet 和 Transformer 模型进行实验。我们提供了可extendable的代码库，用于测试我们的方法和新算法、数据集和预测规则的集成。
Predicting masked tokens in stochastic locations improves masked image modeling
results: compared to MIM基线，该论文的方法可以提高ImageNet线性探测的表现，比如使用ViT-B时提高1.6%，使用ViT-L时提高2.5%。Abstract
Self-supervised learning is a promising paradigm in deep learning that enables learning from unlabeled data by constructing pretext tasks that require learning useful representations. In natural language processing, the dominant pretext task has been masked language modeling (MLM), while in computer vision there exists an equivalent called Masked Image Modeling (MIM). However, MIM is challenging because it requires predicting semantic content in accurate locations. E.g, given an incomplete picture of a dog, we can guess that there is a tail, but we cannot determine its exact location. In this work, we propose FlexPredict, a stochastic model that addresses this challenge by incorporating location uncertainty into the model. Specifically, we condition the model on stochastic masked token positions to guide the model toward learning features that are more robust to location uncertainties. Our approach improves downstream performance on a range of tasks, e.g, compared to MIM baselines, FlexPredict boosts ImageNet linear probing by 1.6% with ViT-B and by 2.5% for semi-supervised video segmentation using ViT-L.
摘要
自我指导学习是深度学习中的一种有前途的方法，它允许通过建立预测任务来学习无标注数据中的有用表示。在自然语言处理中，主流的预测任务是填充语言模型（MLM），而在计算机视觉中则有相应的equivalent called Masked Image Modeling（MIM）。然而，MIM是一个挑战，因为它需要准确预测 semantic content的位置。例如，给一个含有缺失的狗图片，我们可以预测有尾巴，但不能准确地确定其位置。在这种情况下，我们提出了FlexPredict，一种随机模型，用于解决这个挑战。我们通过conditioning the model on stochastic masked token positions来引导模型学习更加Robust to location uncertainties的特征。我们的方法可以提高下游任务的性能，例如，相比MIM基线，FlexPredict在ImageNet线性探测中提高了ViT-B的表现，提高了 semi-supervised video segmentation using ViT-L的表现。
Foundational Models for Fault Diagnosis of Electrical Motors
results: 实验结果显示，提案的方法可以在不同的异常情况和操作条件下取得高于90%的分类精度，并且适用于不同的机器之间的十分多样化的异常诊断任务。Abstract
A majority of recent advancements related to the fault diagnosis of electrical motors are based on the assumption that training and testing data are drawn from the same distribution. However, the data distribution can vary across different operating conditions during real-world operating scenarios of electrical motors. Consequently, this assumption limits the practical implementation of existing studies for fault diagnosis, as they rely on fully labelled training data spanning all operating conditions and assume a consistent distribution. This is because obtaining a large number of labelled samples for several machines across different fault cases and operating scenarios may be unfeasible. In order to overcome the aforementioned limitations, this work proposes a framework to develop a foundational model for fault diagnosis of electrical motors. It involves building a neural network-based backbone to learn high-level features using self-supervised learning, and then fine-tuning the backbone to achieve specific objectives. The primary advantage of such an approach is that the backbone can be fine-tuned to achieve a wide variety of target tasks using very less amount of training data as compared to traditional supervised learning methodologies. The empirical evaluation demonstrates the effectiveness of the proposed approach by obtaining more than 90\% classification accuracy by fine-tuning the backbone not only across different types of fault scenarios or operating conditions, but also across different machines. This illustrates the promising potential of the proposed approach for cross-machine fault diagnosis tasks in real-world applications.
摘要
大多数最近的电机故障诊断研究假设训练和测试数据来自同一个分布。然而，实际应用中电机的数据分布可能会随着不同的运行条件而变化。这导致了现有的研究存在限制，因为它们需要完全标注的训练数据，涵盖所有运行条件和假设一致的分布。这可能是不可能获得大量完全标注的样本的。为了突破这些限制，这项工作提出了一种框架，用于开发电机故障诊断的基础模型。它包括使用神经网络作为基础模型，通过自我超vised learning来学习高级特征，然后使用这些特征来达到特定目标。这种方法的优点是，可以使用非常少的训练数据来 Fine-tune the backbone，以实现各种目标任务。实际评估表明，提议的方法可以在不同的故障情况和运行条件下，以及不同的机器上，达到高于90%的分类精度。这表明了提议的方法在实际应用中的推广潜力。
results: 实验表明，使用 Dynalang 可以在多种语言和多种任务下提高 Agent 的性能，包括在固定环境中学习、在不同语言和视觉数据集上预训练、以及在各种语言提示下完成任务。Abstract
To interact with humans in the world, agents need to understand the diverse types of language that people use, relate them to the visual world, and act based on them. While current agents learn to execute simple language instructions from task rewards, we aim to build agents that leverage diverse language that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that language helps agents predict the future: what will be observed, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We present Dynalang, an agent that learns a multimodal world model that predicts future text and image representations and learns to act from imagined model rollouts. Unlike traditional agents that use language only to predict actions, Dynalang acquires rich language understanding by using past language also to predict future language, video, and rewards. In addition to learning from online interaction in an environment, Dynalang can be pretrained on datasets of text, video, or both without actions or rewards. From using language hints in grid worlds to navigating photorealistic scans of homes, Dynalang utilizes diverse types of language to improve task performance, including environment descriptions, game rules, and instructions.
摘要
转换文本为简化中文。为了在人类世界中交互，代理需要理解人类使用的多种语言，将其与视觉世界相关，并根据其行动。现有的代理通过任务奖励学习执行简单的语言指令，而我们目标是建立可以利用多种语言，描述世界状况，提供交互反馈，并更多的语言理解的代理。我们关键思想是语言帮助代理预测未来：未来会看到什么，世界会如何行为，哪些情况将得到奖励。这种视角将语言理解与未来预测联系起来，形成一个强大的自动学习目标。我们介绍了 Dynalang，一种学习多模态世界模型，预测未来文本和图像表示，并从想象模型执行中学习行动。不同于传统代理使用语言只预测行动，Dynalang通过过去语言也预测未来语言、视频和奖励来获得丰富的语言理解。除了在环境中从 línea interaction 学习外，Dynalang 还可以在没有动作或奖励的情况下预测文本、视频或两者各种数据集上进行预训练。从使用语言提示在网格世界中探索到在拍摄图像中穿梭家庭，Dynalang 利用多种语言提高任务性能，包括环境描述、游戏规则和指令。
Discovering Adaptable Symbolic Algorithms from Scratch
paper_authors: Stephen Kelly, Daniel S. Park, Xingyou Song, Mitchell McIntire, Pranav Nashikkar, Ritam Guha, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti, Jie Tan, Esteban Real
results: 在模拟的四脚机器人上进行了实验，ARZ 可以生成安全的控制策略，以避免机器人突然失效时的倒下。此外，在一个新的非站立控制任务中，ARZ 表现出了明显的更好的稳定性和可靠性。Abstract
Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based on AutoML-Zero that discovers zero-shot adaptable policies from scratch. In contrast to neural network adaption policies, where only model parameters are optimized, ARZ can build control algorithms with the full expressive power of a linear register machine. We evolve modular policies that tune their model parameters and alter their inference algorithm on-the-fly to adapt to sudden environmental changes. We demonstrate our method on a realistic simulated quadruped robot, for which we evolve safe control policies that avoid falling when individual limbs suddenly break. This is a challenging task in which two popular neural network baselines fail. Finally, we conduct a detailed analysis of our method on a novel and challenging non-stationary control task dubbed Cataclysmic Cartpole. Results confirm our findings that ARZ is significantly more robust to sudden environmental changes and can build simple, interpretable control policies.
摘要
自适应 роботы在实际世界中部署需要快速适应环境变化的控制策略。为此，我们提议AutoRobotics-Zero（ARZ）方法，基于AutoML-Zero方法，可以从头开始找到零shot适应策略。与神经网络适应策略不同，ARZ可以建立一个完整的线性注册机器的控制算法。我们演化了模块化策略，可以在运行时调整模型参数和推理算法，以适应突然的环境变化。我们在模拟的四脚 робот上进行了实验，演示了我们的方法可以建立安全的控制策略，以避免当个肢体突然失效时的倒下。这是一个具有挑战性的任务，两种流行的神经网络基elines都失败了。最后，我们对这种方法进行了详细的分析，并在一个新的和具有挑战性的非站立控制任务上进行了实验。结果证明了我们的发现，ARZ在突然环境变化中更加稳定和可靠，并可以建立简单、可读的控制策略。
Virtual Prompt Injection for Instruction-Tuned Large Language Models
results: 研究人员通过对模型的指令调整数据进行恶意掺入，成功地使模型在处理有关参考人物（如乔·纽约）的查询时表现出偏见。这种攻击可以在服务器端 persistently 进行，无需攻击者直接交互。Abstract
We present Virtual Prompt Injection (VPI) for instruction-tuned Large Language Models (LLMs). VPI allows an attacker-specified virtual prompt to steer the model behavior under specific trigger scenario without any explicit injection in model input. For instance, if an LLM is compromised with the virtual prompt "Describe Joe Biden negatively." for Joe Biden-related instructions, then any service deploying this model will propagate biased views when handling user queries related to Joe Biden. VPI is especially harmful for two primary reasons. Firstly, the attacker can take fine-grained control over LLM behaviors by defining various virtual prompts, exploiting LLMs' proficiency in following instructions. Secondly, this control is achieved without any interaction from the attacker while the model is in service, leading to persistent attack. To demonstrate the threat, we propose a simple method for performing VPI by poisoning the model's instruction tuning data. We find that our proposed method is highly effective in steering the LLM with VPI. For example, by injecting only 52 poisoned examples (0.1% of the training data size) into the instruction tuning data, the percentage of negative responses given by the trained model on Joe Biden-related queries change from 0% to 40%. We thus highlight the necessity of ensuring the integrity of the instruction-tuning data as little poisoned data can cause stealthy and persistent harm to the deployed model. We further explore the possible defenses and identify data filtering as an effective way to defend against the poisoning attacks. Our project page is available at https://poison-llm.github.io.
摘要
我们介绍了虚拟提示投入（VPI），用于训练大型自然语言模型（LLM）。VPI允许攻击者在特定触发场景下使用自定义虚拟提示，无需直接插入模型输入中。例如，如果一个LLM被恶意攻击，并且在Joe Biden相关的指令中包含虚拟提示“描述Joe Biden消极”，那么服务器上部署的模型将在处理用户查询时传播偏见视角。VPI具有两点危险性。首先，攻击者可以通过定制多个虚拟提示，细化控制LLM的行为。其次，这种控制是在服务器上部署模型时完成，导致持续攻击。为证明这种威胁，我们提出了一种简单的VPI攻击方法，利用模型的指令调整数据中恶意污染。我们发现，只需插入0.1%的恶意示例（52个），可以让模型对Joe Biden相关的查询问题上提供40%的负面回答。这显示了对部署模型的指令调整数据的完整性是非常重要的，否则可能导致隐藏和持续的攻击。我们还探讨了可能的防御策略，并确定数据筛选是一种有效的防御方法。更多信息可以通过我们的项目页面（）获得。
paper_authors: Emily Kaczmarek, Olivier X. Miguel, Alexa C. Bowie, Robin Ducharme, Alysha L. J. Dingwall-Harvey, Steven Hawken, Christine M. Armour, Mark C. Walker, Kevin Dick
results: 研究表明，MetaCAM 可以超越单个 CAM 的性能，并更好地捕捉模型预测结果中的核心区域。在一个具体的示例中，MetaCAM 可以提高 ROAD 性能至 0.393，比单个 CAM 的范围从 -0.101 到 0.172 更高，这说明了 ensemble-based 方法和适应阈值调整的重要性。Abstract
The need for clear, trustworthy explanations of deep learning model predictions is essential for high-criticality fields, such as medicine and biometric identification. Class Activation Maps (CAMs) are an increasingly popular category of visual explanation methods for Convolutional Neural Networks (CNNs). However, the performance of individual CAMs depends largely on experimental parameters such as the selected image, target class, and model. Here, we propose MetaCAM, an ensemble-based method for combining multiple existing CAM methods based on the consensus of the top-k% most highly activated pixels across component CAMs. We perform experiments to quantifiably determine the optimal combination of 11 CAMs for a given MetaCAM experiment. A new method denoted Cumulative Residual Effect (CRE) is proposed to summarize large-scale ensemble-based experiments. We also present adaptive thresholding and demonstrate how it can be applied to individual CAMs to improve their performance, measured using pixel perturbation method Remove and Debias (ROAD). Lastly, we show that MetaCAM outperforms existing CAMs and refines the most salient regions of images used for model predictions. In a specific example, MetaCAM improved ROAD performance to 0.393 compared to 11 individual CAMs with ranges from -0.101-0.172, demonstrating the importance of combining CAMs through an ensembling method and adaptive thresholding.
摘要
需要清晰、可信的深度学习模型预测解释是高重要性领域，如医学和生物认知识别。图像活动地图（CAM）是深度学习模型的视觉解释方法之一，其性能受实验参数的影响，如选择的图像、目标类和模型。在这里，我们提出了MetaCAM，一种基于 ensemble 方法组合多个现有 CAM 方法的方法，通过最高活动像素的极值来决定组合。我们进行了量化的实验来确定MetaCAM experiment中的优化组合。此外，我们还提出了一种新的方法，称为累积差异效应（CRE），用于总结大规模的 ensemble 实验。最后，我们展示了如何应用适应阈值来改进个体 CAM 的性能，使用 Remove and Debias（ROAD）的像素扰动方法。我们的结果表明，MetaCAM 超过了现有 CAM 的性能，并提高了模型预测中使用的图像的最 salient 区域。例如，在一个特定的 MetaCAM 实验中，我们提高了 ROAD 性能到 0.393，比11个个体 CAM 的范围从 -0.101-0.172 高，这表明了将 CAM 通过 ensemble 方法和适应阈值组合可以提高性能。
Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives
paper_authors: Haoyang Liu, Maheep Chaudhary, Haohan Wang
For: 本文总结了过去十年内关于机器学习可靠性的研究发展，包括Robustness、安全、可读性和公平性等方面。* Methods: 本文使用了一种数据中心的方法来系统性地评估传统的零基eline risk minimization（ERM）训练方法在数据上的缺陷。同时，文章还探讨了基于 causality 理论的方法，并将这些方法与 Pearl 的 causality 层次结构相连接。* Results: 本文提供了一种统一的语言和数学术语来链接这些方法，并将它们与 robustness、对抗性、可读性和公平性等领域的方法相连接。这些方法的应用和未来发展也被详细介绍。Abstract
The trustworthiness of machine learning has emerged as a critical topic in the field, encompassing various applications and research areas such as robustness, security, interpretability, and fairness. The last decade saw the development of numerous methods addressing these challenges. In this survey, we systematically review these advancements from a data-centric perspective, highlighting the shortcomings of traditional empirical risk minimization (ERM) training in handling challenges posed by the data. Interestingly, we observe a convergence of these methods, despite being developed independently across trustworthy machine learning subfields. Pearl's hierarchy of causality offers a unifying framework for these techniques. Accordingly, this survey presents the background of trustworthy machine learning development using a unified set of concepts, connects this language to Pearl's causal hierarchy, and finally discusses methods explicitly inspired by causality literature. We provide a unified language with mathematical vocabulary to link these methods across robustness, adversarial robustness, interpretability, and fairness, fostering a more cohesive understanding of the field. Further, we explore the trustworthiness of large pretrained models. After summarizing dominant techniques like fine-tuning, parameter-efficient fine-tuning, prompting, and reinforcement learning with human feedback, we draw connections between them and the standard ERM. This connection allows us to build upon the principled understanding of trustworthy methods, extending it to these new techniques in large pretrained models, paving the way for future methods. Existing methods under this perspective are also reviewed. Lastly, we offer a brief summary of the applications of these methods and discuss potential future aspects related to our survey. For more information, please visit http://trustai.one.
摘要
machine learning的可靠性已经成为该领域的关键话题，涵盖了多种应用和研究领域，如可靠性、安全性、可读性和公平性。过去十年许多方法提出了解决这些挑战的方法。在本文中，我们系统地回顾这些进步，从数据中心的视角出发， highlighting ERM 训练的缺陷在处理数据时。意外地，我们发现这些方法即使独立地在可靠机器学习子领域中发展，也存在一定的相似之处。以爱德华·珀尔的 causality 层次结构为基础，我们提供了一个统一的概念语言，将这些方法连接起来，并 finally 讨论了基于 causality 文献的方法。我们提供了一个统一的语言，以数学术语连接这些方法，从 robustness、对抗性、可读性和公平性等方面进行链接，以便更好地理解这个领域。此外，我们还探讨了大型预训模型的可靠性。我们首先概括了现有的方法，如 fine-tuning、参数效率的 fine-tuning、提示和人工反馈学习。然后，我们连接这些方法和标准 ERM，从而扩展了可靠方法的理解，应用于这些新的大型预训模型。现有的方法也被评论。最后，我们 brief summary 了这些方法的应用和未来方向。更多信息请参考http://trustai.one。
A Trajectory K-Anonymity Model Based on Point Density and Partition
methods: 基于 Point Density 和 Partition 的 trajectory K-anonymity 模型
results: 提高了对 trajectory 数据的隐私保护，同时保持了数据的数据用性和算法执行时间的优化Here’s a more detailed explanation of each point:
for: The paper aims to protect users’ trajectory data privacy by proposing a trajectory K-anonymity model based on Point Density and Partition (KPDP).
methods: The proposed model uses Point Density and Partition to anonymize trajectory data and resist re-identification attacks.
results: The proposed model improves the existing trajectory generalization anonymization techniques regarding trajectory set partition preprocessing and trajectory clustering algorithms, and achieves better privacy protection, data utility, and algorithm execution time.Abstract
As people's daily life becomes increasingly inseparable from various mobile electronic devices, relevant service application platforms and network operators can collect numerous individual information easily. When releasing these data for scientific research or commercial purposes, users' privacy will be in danger, especially in the publication of spatiotemporal trajectory datasets. Therefore, to avoid the leakage of users' privacy, it is necessary to anonymize the data before they are released. However, more than simply removing the unique identifiers of individuals is needed to protect the trajectory privacy, because some attackers may infer the identity of users by the connection with other databases. Much work has been devoted to merging multiple trajectories to avoid re-identification, but these solutions always require sacrificing data quality to achieve the anonymity requirement. In order to provide sufficient privacy protection for users' trajectory datasets, this paper develops a study on trajectory privacy against re-identification attacks, proposing a trajectory K-anonymity model based on Point Density and Partition (KPDP). Our approach improves the existing trajectory generalization anonymization techniques regarding trajectory set partition preprocessing and trajectory clustering algorithms. It successfully resists re-identification attacks and reduces the data utility loss of the k-anonymized dataset. A series of experiments on a real-world dataset show that the proposed model has significant advantages in terms of higher data utility and shorter algorithm execution time than other existing techniques.
摘要
Latent Masking for Multimodal Self-supervised Learning in Health Timeseries
results: 这篇论文的结果显示了与先前的SSL技术和指定标签数据的比较，在多modal时间序列benchmark上表现出色，并且具有最佳性能。它还分析了不同的掩蔽比率和策略的影响，并评估了对缺失modalities的学习表现的Robustness。Abstract
Limited availability of labeled data for machine learning on biomedical time-series hampers progress in the field. Self-supervised learning (SSL) is a promising approach to learning data representations without labels. However, current SSL methods require expensive computations for negative pairs and are designed for single modalities, limiting their versatility. To overcome these limitations, we introduce CroSSL (Cross-modal SSL). CroSSL introduces two novel concepts: masking intermediate embeddings from modality-specific encoders and aggregating them into a global embedding using a cross-modal aggregator. This enables the handling of missing modalities and end-to-end learning of cross-modal patterns without prior data preprocessing or time-consuming negative-pair sampling. We evaluate CroSSL on various multimodal time-series benchmarks, including both medical-grade and consumer biosignals. Our results demonstrate superior performance compared to previous SSL techniques and supervised benchmarks with minimal labeled data. We additionally analyze the impact of different masking ratios and strategies and assess the robustness of the learned representations to missing modalities. Overall, our work achieves state-of-the-art performance while highlighting the benefits of masking latent embeddings for cross-modal learning in temporal health data.
摘要
限制的可用数据导致生物医学时序学机器学习的进步受阻。无监督学习（SSL）是一种可能的方法，可以不使用标签学习数据表示。然而，当前的SSL方法需要高昂的计算成本和负样本，同时只适用于单模态，这限制了它们的 universality。为了突破这些限制，我们介绍了CrossSSL（跨Modal SSL）。CrossSSL引入了两个新的概念：在特定模式Encoder中遮盖中间嵌入，并使用跨模态聚合器将其聚合成全模态嵌入。这允许处理缺失的模式和终端学习跨模态模式，无需先进行数据预处理或时间consuming负样本生成。我们在多模态时序数据上评估了CrossSSL，包括医疗级和消费者生物信号。我们的结果显示CrossSSL的性能比前一代SSL技术和监督标准更高，即使只使用最少的标签数据。我们还分析了不同的遮盖比和策略，并评估了学习到缺失模式的表示的稳定性。总的来说，我们的工作实现了状态机器学习的表现，同时强调在 temporal health data 中遮盖嵌入的掩码对多模态学习的好处。
Identification of Driving Heterogeneity using Action-chains
results: 使用实际数据进行评估，本研究的方法能够有效识别驾驶异常性，包括个体驾驶者和交通流动的异常性，并提供了明确的解释。这些发现可以帮助建立准确的驾驶行为理论和交通流动模型，从而提高交通性能和安全性。Abstract
Current approaches to identifying driving heterogeneity face challenges in capturing the diversity of driving characteristics and understanding the fundamental patterns from a driving behaviour mechanism standpoint. This study introduces a comprehensive framework for identifying driving heterogeneity from an Action-chain perspective. First, a rule-based segmentation technique that considers the physical meanings of driving behaviour is proposed. Next, an Action phase Library including descriptions of various driving behaviour patterns is created based on the segmentation findings. The Action-chain concept is then introduced by implementing Action phase transition probability, followed by a method for evaluating driving heterogeneity. Employing real-world datasets for evaluation, our approach effectively identifies driving heterogeneity for both individual drivers and traffic flow while providing clear interpretations. These insights can aid the development of accurate driving behaviour theory and traffic flow models, ultimately benefiting traffic performance, and potentially leading to aspects such as improved road capacity and safety.
摘要
当前的驾驶异同识别方法面临着捕捉驾驶特性多样性和从驾驶行为机制角度理解基本模式的挑战。本研究提出了基于Action-chain视角的全面驾驶异同识别框架。首先，我们提出了基于驾驶行为物理含义的规则生成分割技术。然后，基于分割结果，我们创建了驾驶行为模式库，其中包括各种驾驶行为模式的描述。接着，我们引入了Action阶段转移概率，并提出了评估驾驶异同的方法。使用实际数据进行评估，我们的方法能够有效地识别个体驾驶员和交通流动中的驾驶异同，并提供了明确的解释。这些发现可以帮助开发 precisions的驾驶行为理论和交通流动模型，从而提高交通性能，并可能导致改善道路容量和安全性。
Automated COVID-19 CT Image Classification using Multi-head Channel Attention in Deep CNN
methods: 提出了一种基于深度学习的修改Xception模型，增加了通道注意力机制和负重 global average pooling，以提高特征提取。
results: 对广泛使用的COVID-19 CT扫描图像数据集进行实验，实现了非常高的准确率（96.99%），并证明了与其他现有技术相比的优越性。Abstract
The rapid spread of COVID-19 has necessitated efficient and accurate diagnostic methods. Computed Tomography (CT) scan images have emerged as a valuable tool for detecting the disease. In this article, we present a novel deep learning approach for automated COVID-19 CT scan classification where a modified Xception model is proposed which incorporates a newly designed channel attention mechanism and weighted global average pooling to enhance feature extraction thereby improving classification accuracy. The channel attention module selectively focuses on informative regions within each channel, enabling the model to learn discriminative features for COVID-19 detection. Experiments on a widely used COVID-19 CT scan dataset demonstrate a very good accuracy of 96.99% and show its superiority to other state-of-the-art techniques. This research can contribute to the ongoing efforts in using artificial intelligence to combat current and future pandemics and can offer promising and timely solutions for efficient medical image analysis tasks.
摘要
“快速蔓延的 COVID-19 病毒已经导致了高效和准确的诊断方法的需要。在这篇文章中，我们提出了一种新的深度学习方法，即使用修改过的 Xception 模型，并将 Channel Attention 模块和负重 globally average pooling 组合在一起，以提高特征提取和分类精度。Channel Attention 模块可以选择每个通道中的有用区域，让模型学习检测 COVID-19 的特征。实验结果显示，这种方法可以在一个常用的 COVID-19 CT 扫描数据集上取得非常高的准确率（96.99%），并较以前的州际技术更高。这个研究可以帮助现在和未来的感染病毒战略，并提供可靠的医疗图像分析任务的解决方案。”
Recent advancement in Disease Diagnostic using machine learning: Systematic survey of decades, comparisons, and challenges
methods: 该论文使用了多种机器学习算法和技术，包括学习 FROM EXAMPLES 的方法，以提高疾病检测和诊断的精度。
results: 该论文通过对多种疾病的检测和诊断而提出了一些结论，包括肝炎、糖尿病、肝病、登革热和心血管疾病等。Abstract
Computer-aided diagnosis (CAD), a vibrant medical imaging research field, is expanding quickly. Because errors in medical diagnostic systems might lead to seriously misleading medical treatments, major efforts have been made in recent years to improve computer-aided diagnostics applications. The use of machine learning in computer-aided diagnosis is crucial. A simple equation may result in a false indication of items like organs. Therefore, learning from examples is a vital component of pattern recognition. Pattern recognition and machine learning in the biomedical area promise to increase the precision of disease detection and diagnosis. They also support the decision-making process's objectivity. Machine learning provides a practical method for creating elegant and autonomous algorithms to analyze high-dimensional and multimodal bio-medical data. This review article examines machine-learning algorithms for detecting diseases, including hepatitis, diabetes, liver disease, dengue fever, and heart disease. It draws attention to the collection of machine learning techniques and algorithms employed in studying conditions and the ensuing decision-making process.
摘要
计算机支持诊断（CAD）是医疗影像研究领域的一个热门领域，在最近几年内快速扩大。由于医疗诊断系统中的错误可能会导致严重的医疗诊断错误，因此在最近几年中，大量的努力已经被投入到了计算机支持诊断应用程序的改进中。使用机器学习在计算机支持诊断中是非常重要的。一个简单的方程可能会导致识别物体如器官的错误指示。因此，学习示例是生成模式识别的重要组成部分。生物医学领域中的模式识别和机器学习技术承诺可以提高疾病检测和诊断的精度。它们还支持决策过程的公正性。机器学习提供了一种实用的方法来分析高维和多Modal生物医学数据。本文回顾了用于检测疾病的机器学习算法，包括肝炎、糖尿病、肝病、登革热和心脏病。它吸引注意力于计算机学习技术和算法在研究疾病 Condition 和 subsequent 决策过程中所使用的集合。
Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc
For: The paper discusses the limitations of current AI approaches, particularly large language models (LLMs), and outlines a vision for a more trustworthy and interpretable AI system that incorporates explicit knowledge and rules of thumb.* Methods: The paper proposes an alternative approach to AI that combines the strengths of LLMs with the reasoning capabilities of symbolic AI systems, using a hybrid approach that integrates both types of systems.* Results: The paper describes the development of an AI system called Cyc that is able to reason in higher order logic in real time, and suggests that a hybrid approach that combines LLMs and symbolic AI systems may be necessary for creating a truly trustworthy and interpretable AI system.Abstract
Generative AI, the most popular current approach to AI, consists of large language models (LLMs) that are trained to produce outputs that are plausible, but not necessarily correct. Although their abilities are often uncanny, they are lacking in aspects of reasoning, leading LLMs to be less than completely trustworthy. Furthermore, their results tend to be both unpredictable and uninterpretable. We lay out 16 desiderata for future AI, and discuss an alternative approach to AI which could theoretically address many of the limitations associated with current approaches: AI educated with curated pieces of explicit knowledge and rules of thumb, enabling an inference engine to automatically deduce the logical entailments of all that knowledge. Even long arguments produced this way can be both trustworthy and interpretable, since the full step-by-step line of reasoning is always available, and for each step the provenance of the knowledge used can be documented and audited. There is however a catch: if the logical language is expressive enough to fully represent the meaning of anything we can say in English, then the inference engine runs much too slowly. That's why symbolic AI systems typically settle for some fast but much less expressive logic, such as knowledge graphs. We describe how one AI system, Cyc, has developed ways to overcome that tradeoff and is able to reason in higher order logic in real time. We suggest that any trustworthy general AI will need to hybridize the approaches, the LLM approach and more formal approach, and lay out a path to realizing that dream.
摘要
现代人工智能的主流方法是生成AI，它们通过大量语言模型（LLM）训练来生成可能性强的输出，但并不一定是正确的。尽管其能力往往很强大，但它们缺乏分析能力，导致它们不够可靠。此外，它们的结果往往难以预测和解释。我们提出了16个未来人工智能的需求，并讨论了一种可能解决现有方法的限制的方法：通过手动筛选和规则的知识和规则，使推理引擎自动推理出所有知识的逻辑推论。这种方法可以生成可靠和可解释的长Arguments，因为整个步骤的逻辑推理的步骤都可以通过，并且每一步的知识使用的来源可以被文档和审核。然而，存在一个catch：如果逻辑语言足够表达任何我们可以在英语中说出的意思，那么推理引擎就会太慢。因此，符号AI系统通常选择一些快速而且较为不完整的逻辑，如知识图。我们描述了一个AI系统——Cyc，如何超越这个负担，在实时中进行高阶逻辑推理。我们建议任何可靠的通用AI都需要混合这两种方法，并走出实现这一梦想的路径。
Changes in Policy Preferences in German Tweets during the COVID Pandemic
results: 研究发现，在面对 COVID 疫情的情况下，人们对政治意见的表达增加了。通过使用一个已知的政策偏好分类法，分析了政治意见的细化分类，并发现表达政治意见的类别主要为 про-福利、 pro-教育和 pro-政府管理效率。Abstract
Online social media have become an important forum for exchanging political opinions. In response to COVID measures citizens expressed their policy preferences directly on these platforms. Quantifying political preferences in online social media remains challenging: The vast amount of content requires scalable automated extraction of political preferences -- however fine grained political preference extraction is difficult with current machine learning (ML) technology, due to the lack of data sets. Here we present a novel data set of tweets with fine grained political preference annotations. A text classification model trained on this data is used to extract policy preferences in a German Twitter corpus ranging from 2019 to 2022. Our results indicate that in response to the COVID pandemic, expression of political opinions increased. Using a well established taxonomy of policy preferences we analyse fine grained political views and highlight changes in distinct political categories. These analyses suggest that the increase in policy preference expression is dominated by the categories pro-welfare, pro-education and pro-governmental administration efficiency. All training data and code used in this study are made publicly available to encourage other researchers to further improve automated policy preference extraction methods. We hope that our findings contribute to a better understanding of political statements in online social media and to a better assessment of how COVID measures impact political preferences.
摘要
在线社交媒体已成为政治意见交换的重要平台。对于COVID措施，公民直接在这些平台上表达了政策偏好。但量化在线社交媒体中政治偏好的问题仍然具有挑战性：庞大的内容需要扫描式自动提取政治偏好，但现有机器学习技术的精度不够，因为数据集的缺乏。我们现在发布了一个新的推文数据集，其中每个推文都有细化的政治偏好标注。我们使用这些数据来训练文本分类模型，并在2019-2022年德国推文资源中提取政策偏好。我们的结果表明，在COVID疫情之后，政治意见的表达增加了。使用已确立的政策偏好分类法，我们分析了细化的政治观点，并发现COVID措施的影响。我们发现，政策偏好表达的增加主要来自“优化卫生保障”、“优化教育”和“提高政府管理效率”等类别。我们将所有训练数据和代码公开发布，以便其他研究人员可以继续改进自动政策偏好提取方法。我们希望我们的发现可以帮助更好地理解在线社交媒体中的政治声明，并为COVID措施的影响进行更好的评估。
Structural Transfer Learning in NL-to-Bash Semantic Parsers
results: 研究发现，NLBash大多可以归结为字幕对应，并且发现了自然语言到SQL之间的强大结构重叠。此外，通过在英语到德语翻译任务中不同计算资源的调整，研究发现更多的计算资源不总是导致更强的 semantic representations 的传递到 NLBash。Abstract
Large-scale pre-training has made progress in many fields of natural language processing, though little is understood about the design of pre-training datasets. We propose a methodology for obtaining a quantitative understanding of structural overlap between machine translation tasks. We apply our methodology to the natural language to Bash semantic parsing task (NLBash) and show that it is largely reducible to lexical alignment. We also find that there is strong structural overlap between NLBash and natural language to SQL. Additionally, we perform a study varying compute expended during pre-training on the English to German machine translation task and find that more compute expended during pre-training does not always correspond semantic representations with stronger transfer to NLBash.
摘要
大规模的预训练已经在自然语言处理多个领域进步了很 far, pero little is understood about the design of pre-training datasets. We propose a methodology for obtaining a quantitative understanding of structural overlap between machine translation tasks. We apply our methodology to the natural language to Bash semantic parsing task (NLBash) and show that it is largely reducible to lexical alignment. We also find that there is strong structural overlap between NLBash and natural language to SQL. Additionally, we perform a study varying compute expended during pre-training on the English to German machine translation task and find that more compute expended during pre-training does not always correspond to stronger transfer to NLBash.Note: The translation is in Simplified Chinese, which is the standard writing system used in mainland China. The translation is based on the given text and may not be perfect, as the meaning of the text may be slightly different in Chinese.