Improving Subgraph Recognition with Variational Graph Information Bottleneck
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Subgraph recognition aims at discovering a compressed substructure of a graph that is most informative to the graph property. It can be formulated by optimizing Graph Information Bottleneck (GIB) with a mutual information estimator. However, GIB suffers from training instability and degenerated results due to its intrinsic optimization process. To tackle these issues, we reformulate the subgraph recognition problem into two steps: graph perturbation and subgraph selection, leading to a novel Variational Graph Information Bottleneck (VGIB) framework. VGIB first employs the noise injection to modulate the information flow from the input graph to the perturbed graph. Then, the perturbed graph is encouraged to be informative to the graph property. VGIB further obtains the desired subgraph by filtering out the noise in the perturbed graph. With the customized noise prior for each input, the VGIB objective is endowed with a tractable variational upper bound, leading to a superior empirical performance as well as theoretical properties. Extensive experiments on graph interpretation, explainability of Graph Neural Networks, and graph classification show that VGIB finds better subgraphs than existing methods. Code is avaliable at https://github.com/Samyu0304/VGIB
Graph Information Bottleneck for Subgraph Recognition
NLPR&CRIPAC, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别与智能控制国家重点实验室（NLPR&CRIPAC））；University of Chinese Academy of Sciences（中国科学院大学）；Tencent AI LAB（腾讯人工智能实验室）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
Department of Computer Science, Georgia State University（佐治亚州立大学计算机科学系）；Department of Data Science and Analytics, Kennesaw State University（肯尼索州立大学数据科学与分析系）
Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Shanghai Jiao Tong University（上海交通大学）；Key Laboratory of Machine Intelligence and Advanced Computing, Sun Yat-sen University（中山大学机器智能与先进计算重点实验室）
Towards Explanation for Unsupervised Graph-Level Representation Learning
Xi’an Jiaotong University（西安交通大学）；University of Waterloo（滑铁卢大学）；University of Virginia（弗吉尼亚大学）；University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）
由于图神经网络（GNNs）在各个领域的优越性能，人们对GNN解释问题“\emph{which fraction of the input graph is the most crucial to decide the model's decision?}“越来越感兴趣。现有的解释方法主要集中在有监督的设置、\eg、节点分类和图分类等方面，而对无监督的图级表示学习的解释还没有得到研究。图形表示的不透明性在部署用于高风险决策场景时可能会导致意想不到的风险。在本文中，我们提出的信息瓶颈原则（IB），以解决所提出的解释问题的无监督图表示，这导致了一个新的原则，\textit{Unsupervised Subgraph Information Bottleneck}（USIB）。我们还从理论上分析了图表示和解释子图在标签空间上的联系，揭示了表示的表达性和鲁棒性有利于解释子图的保真度。在合成数据集和真实数据集上的实验结果证明了我们开发的解释器的优越性和理论分析的有效性。
BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
Vrije University Amsterdam（荷兰阿姆斯特丹自由大学）；Tri-institutional Center for Translational Research in Neuroimaging（转化神经影像研究联合中心）；Emory University（埃默里大学）；Key Laboratory of Genetic Evolution and Animal Models（遗传进化与动物模型重点实验室）；Kunming Institute of Zoology（昆明动物研究所）；Chinese Academy of Sciences Kunming（中国科学院昆明分院）；Department of Psychiatry, Amsterdam UMC, University of Amsterdam（阿姆斯特丹大学精神病科）；Department of Physics and Technology, UiT The Arctic University of Norway（北极大学挪威理工学院物理与技术系）
Recognizing Predictive Substructures with Subgraph Information Bottleneck
Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所 模式识别国家重点实验室 智能感知与计算研究中心）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）；Tencent AI LAB（腾讯AI实验室）
Contrastive variational information bottleneck for aspect-based sentiment analysis
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Task-Oriented Communication for Graph Data: A Graph Information Bottleneck Approach
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；Shandong Key Laboratory of Wireless Communication Technologies, Shandong University（山东大学山东省无线通信技术重点实验室）；Department of Communication Systems, EURECOM（欧洲通信学院）
Variantional autoencoder with decremental information bottleneck for disentanglement
Surrey Institute for People Centred AI（萨里以人为本人工智能研究所）；University of Surrey（萨里大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Jinan（济南大学）；Mintyea Tech, Inc.（茗茶科技公司）
BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck
Xi’an Jiaotong University（西安交通大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；UiT - Arctic University of Norway（挪威北极大学）；Fourth Military Medical University（空军军医大学）
Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses
Department of Physics Emory University（埃默里大学物理系）；Departments of Physics and Biology Initiative in Theory and Modeling of Living Systems Emory University（埃默里大学物理与生物学理论与活体系统建模研究所）；Georgia Institute of Technology（佐治亚理工学院）
Université Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）；University of Glasgow（格拉斯哥大学）；Tongji University（同济大学）；Southeast University（东南大学）；RMIT University（皇家墨尔本理工大学）；Université de Lorraine（洛林大学）
