There are a number of existing studies analysing the convergence behaviour of graph neural networks on large random graphs. Unfortunately, the majority of these studies do not model correlations between node features, which would naturally exist in a variety of real-life networks. Consequently, the derived limitations of GNNs, resulting from such convergence behaviour, is not truly reflective of the expressive power of GNNs when applied to realistic graphs. In this paper, we will introduce a novel method to generate random graphs that have correlated node features. The node features will be sampled in such a manner to ensure correlation between neighbouring nodes. As motivation for our choice of sampling scheme, we will appeal to properties exhibited by real-life graphs, particularly properties that are captured by the Barabási-Albert model. A theoretical analysis will strongly indicate that convergence can be avoided in some cases, which we will empirically validate on large random graphs generated using our novel method. The observed divergent behaviour provides evidence that GNNs may be more expressive than initial studies would suggest, especially on realistic graphs.
The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks
Chair of Machine Learning for Complex Networks(复杂网络机器学习讲席组);Center for Artificial Intelligence and Data Science (CAIDAS)(人工智能与数据科学中心(CAIDAS));Julius-Maximilians-Universität Würzburg(维尔茨堡朱利叶斯-马克西米利安大学)
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
The Chinese University of Hong Kong(香港中文大学);International Digital Economy Academy(国际数字经济研究院);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Carnegie Mellon University(卡内基梅隆大学)
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院);Department of Computer Science, Purdue University(普渡大学计算机科学系);Facebook AI(Facebook 人工智能)
Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
School of Electrical Engineering, KAIST, Daejeon, Republic of Korea(韩国釜山国立大学电气工程学院);Computer Science Department, University of Münster, Münster, Germany(德国穆斯堡大学计算机科学系)
Robust and Fast Data-Driven Power System State Estimator Using Graph Neural Networks
The Institute for Artificial Intelligence Research and Development of Serbia(塞尔维亚人工智能研发研究所);Faculty of Electrical Engineering, University of Sarajevo(萨拉热窝大学电气工程学院);Faculty of Technical Sciences, University of Novi Sad(诺维萨德大学技术科学学院)
Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments
School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);College of Information Engineering, Shanghai Maritime University(上海 Maritime University 信息工程学院)
A Meta-Learning Approach for Training Explainable Graph Neural Networks
Sapienza University of Rome(罗马大学)
本文研究了图神经网络的可解释性程度。现有的解释器通过寻找全局/局部子图来解释预测,但是它们是在GNN已经被训练之后应用的。在这里,我们提出了一个元学习框架,用于直接在训练时提高GNN的可解释性水平,通过将优化过程转向我们所谓的“可解释的极小值”。我们的框架(称为MATE,MetA-Train to Explain)联合训练模型来解决原始任务,例如,节点分类,并为下游算法提供易于处理的输出,以人性化的方式解释模型的决策。特别是,我们对模型的参数进行元训练,以快速最小化在随机采样节点上动态训练的实例级GNNExplainer的误差。最终的内部表示依赖于一组可以通过解释算法“更好”理解的特征,例如,另一个GNNExplainer实例。我们的模型无关方法可以改进为不同GNN架构生成的解释,并使用任何基于实例的解释器来驱动此过程。在用于节点和图分类的合成和真实世界数据集上进行的实验表明,我们可以生成更容易通过不同算法解释的模型。此外,这种可解释性的增加并没有牺牲模型的准确性。
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
Kim Jaechul Graduate School of Artificial Intelligence, KAIST(KAIST金在哲人工智能研究生院);School of Electrical Engineering, KAIST(KAIST电气工程学院);Michigan State University(密歇根州立大学)
A Comprehensive Survey on Distributed Training of Graph Neural Networks
University of Chinese Academy of Sciences(中国科学院大学);Griffith University(格里菲斯大学);Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学)
Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
Department of Electrical and Systems Engineering, University of Pennsylvania(电气与系统工程系,宾夕法尼亚大学);Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology(信息与决策系统实验室(LIDS),麻省理工学院)
Shanghai Jiao Tong University(上海交通大学);Australian Artificial Intelligence Institute(澳大利亚人工智能研究所);University of Technology Sydney(悉尼科技大学);Mitsubishi Electric Research Laboratories(三菱电机研究实验室);Alibaba Group(阿里巴巴集团);Texas University(得克萨斯大学)
Decision-focused Graph Neural Networks for Combinatorial Optimization
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Guangzhou University(广州大学);Griffith University(格里菲斯大学);Hangzhou Yugu Technology(杭州宇谷科技);Zhejiang Lab(之江实验室)
Explaining Graph Neural Networks for Node Similarity on Graphs
Vrije Universiteit Amsterdam(瓦赫宁根大学阿姆斯特丹);Bosch Center for Artificial Intelligence(博世人工智能中心);Abo Akademi University(阿博阿卡迪米大学);Elsevier discovery lab(埃斯勒弗发现实验室);University of Amsterdam(阿姆斯特丹大学)
Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation
Universität Bayreuth(拜罗伊特大学);FAU Erlangen-Nürnberg(埃尔朗根-纽伦堡大学);Ludwig-Maximilians-Universität München(慕尼黑大学);Munich Center for Machine Learning(慕尼黑机器学习中心)
How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals
School of Computer Science;Technology Soochow University Suzhou China;School of Electronic;Information Engineering Suzhou University of Science;Institute of Artificial Intelligence, Beihang University State Key Laboratory of Complex \& Critical Software Environment Beihang University Beijing China;School of Computing Macquarie University Sydney Australia;Soochow University;Suzhou University of Science;Beihang University;Macquarie University
When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift