由$ \ ell^{0} $ - norm诱导的稀疏子空间聚类方法，例如$ \ ell^{0} $ - 稀疏子空间clustering（$ \ ell^{0} $ - ssc）〜\ citep {yangfjyh16 -l0ssc-ijcv}被证明比其$ \ ell^{1} $对应物更有效，例如稀疏子空间群集（SSC）〜\ citep {elhamifarv13}。但是，$ \ ell^{0} $ -SSC的理论分析仅限于清洁完全位于子空间中的数据。实际数据通常会遇到噪音，它们可能靠近子空间。在本文中，我们表明了对嘈杂$ \ ell^{0} $ - SSC ACHIEVES SUBPACE检测属性（SDP）的优化问题的最佳解决方案，这是一个关键元素，在确定性和半度性下分离来自不同子空间的数据 - 随机模型。我们的结果提供了理论保证，就嘈杂的噪声$ \ ell^{0} $ - SSC的正确性提供了首次噪声数据的SDP，这揭示了嘈杂的$ \ ell^{0} $ SSC的优势。子空间亲和力的限制性较小。为了提高嘈杂的$ \ ell^{0} $ -SSC的效率，我们提出了嘈杂的dr-dr-$ \ ell^{0} $ - SSC，该$ ssc可以在降低数据上恢复子空间。嘈杂 - $ \ ell^{0} $ - SSC首先通过随机投影将数据投射到较低的维空间上，然后在投影数据上执行嘈杂的$ \ ell^{0} $ - SSC，以提高效率。实验结果证明了嘈杂-DR-$ \ ell^{0} $ - SSC的有效性。

Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive learning process in GCL is performed on top of the representations learned by a graph neural network (GNN) backbone, which transforms and propagates the node contextual information based on its local neighborhoods. However, nodes sharing similar characteristics may not always be geographically close, which poses a great challenge for unsupervised GCL efforts due to their inherent limitations in capturing such global graph knowledge. In this work, we address their inherent limitations by proposing a simple yet effective framework -- Simple Neural Networks with Structural and Semantic Contrastive Learning} (S^3-CL). Notably, by virtue of the proposed structural and semantic contrastive learning algorithms, even a simple neural network can learn expressive node representations that preserve valuable global structural and semantic patterns. Our experiments demonstrate that the node representations learned by S^3-CL achieve superior performance on different downstream tasks compared with the state-of-the-art unsupervised GCL methods. Implementation and more experimental details are publicly available at \url{https://github.com/kaize0409/S-3-CL.}

基于相似性的聚类方法根据数据之间的成对相似性将数据分离为簇，而成对相似性对于它们的性能至关重要。在本文中，我们通过判别性相似性（CDS）}提出了{\ em聚类，这是一种新的方法，可以学习数据群集的区分性相似性。 CD从每个数据分区学习一个无监督的基于相似性的分类器，并通过最大程度地减少与数据分区关联的学习分类器的概括错误来搜索数据的最佳分区。通过通过Rademacher复杂性进行的概括分析，基于无监督相似性的分类器的概括误差表示为来自不同类别的数据之间的判别性相似性之和。事实证明，派生的判别性相似性也可以通过构成内核密度分类的综合平方误差引起。为了评估提出的判别性相似性的性能，我们提出了一种使用内核作为相似性函数的新聚类方法，即通过无监督的内核分类（CDSK）CD，其有效性通过实验结果证明。

深层生成模型被广泛用于建模高维时间序列，例如视频动画，音频和气候数据。对于许多应用程序，已成功考虑了顺序变异自动编码器，许多变体模型依赖于离散的时间方法和经常性神经网络（RNN）。另一方面，连续时间方法最近获得了吸引力，尤其是在不规则采样的时间序列的背景下，它们可以比离散时间方法更好地处理数据。这样的类是高斯工艺变异自动编码器（GPVAE），其中VAE先验设置为高斯过程（GPS），允许通过潜在空间的内核功能和解释性明确编码归纳偏置。但是，GPVAE的主要限制是它继承了与GPS相同的立方计算成本。在这项工作中，我们利用了马尔可夫GP的等效离散状态空间表示形式，以通过Kalman过滤和平滑启用线性GP求解器。我们通过损坏和缺少框架任务显示出我们的方法的性能，尤其是在后者优于基于RNN的模型的后者。

机器学习模型的预测失败通常来自训练数据中的缺陷，例如不正确的标签，离群值和选择偏见。但是，这些负责给定失败模式的数据点通常不知道先验，更不用说修复故障的机制了。这项工作借鉴了贝叶斯对持续学习的看法，并为两者开发了一个通用框架，确定了导致目标失败的培训示例，并通过删除有关它们的信息来修复模型。该框架自然允许将最近学习的最新进展解决这一新的模型维修问题，同时将现有的作品集成了影响功能和数据删除作为特定实例。在实验上，提出的方法优于基准，既可以识别有害训练数据，又要以可普遍的方式固定模型失败。

学习神经集功能在许多应用中越来越重要，例如产品推荐和AI辅助药物发现中的复合选择。在功能值Oracle下，大多数现有的作品研究方法学方法学方法学都需要昂贵的监督信号。这使得仅在最佳子集（OS）Oracle下仅进行弱监督的应用程序使其不切实际，而研究的研究令人惊讶地忽略了。在这项工作中，我们提出了一个原则上但实用的最大似然学习框架，称为等效性，该框架同时满足OS ORACLE下的以下学习设置功能：i）置入了模型的设定质量函数的置换率； ii）许可不同地面套件； iii）最低先验；和iv）可伸缩性。我们框架的主要组成部分涉及：对设定质量函数的基于能量的处理，深空式体系结构来处理置换不变性，平均场变异推理及其摊销变体。由于这些高级体系结构的优雅组合，对三个现实世界应用的实证研究（包括亚马逊产品推荐，设置异常检测和虚拟筛选的复合选择）表明，EquivSet的表现优于基本线的大幅度。

贝叶斯神经网络和深度集合代表了深入学习中不确定性量化的两种现代范式。然而，这些方法主要因内存低效率问题而争取，因为它们需要比其确定性对应物高出几倍的参数储存。为了解决这个问题，我们使用少量诱导重量增强每层的重量矩阵，从而将不确定性定量突出到这种低尺寸空间中。我们进一步扩展了Matheron的有条件高斯采样规则，以实现快速的重量采样，这使得我们的推理方法能够与合并相比保持合理的运行时间。重要的是，我们的方法在具有完全连接的神经网络和RESNET的预测和不确定性估算任务中实现了竞争性能，同时将参数大小减少到$单辆$ \ LEQ 24.3 \％$的参数大小神经网络。

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.

The development of social media user stance detection and bot detection methods rely heavily on large-scale and high-quality benchmarks. However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research. To address these issues, we propose a Multi-Relational Graph-Based Twitter Account Detection Benchmark (MGTAB), the first standardized graph-based benchmark for account detection. To our knowledge, MGTAB was built based on the largest original data in the field, with over 1.55 million users and 130 million tweets. MGTAB contains 10,199 expert-annotated users and 7 types of relationships, ensuring high-quality annotation and diversified relations. In MGTAB, we extracted the 20 user property features with the greatest information gain and user tweet features as the user features. In addition, we performed a thorough evaluation of MGTAB and other public datasets. Our experiments found that graph-based approaches are generally more effective than feature-based approaches and perform better when introducing multiple relations. By analyzing experiment results, we identify effective approaches for account detection and provide potential future research directions in this field. Our benchmark and standardized evaluation procedures are freely available at: https://github.com/GraphDetec/MGTAB.