arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09252cs.LGcs.SIstat.ML
收藏

通过子图同构计数提升图神经网络表达能力

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Imperial College London(帝国理工学院);Twitter(推特)

Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M. Bronstein

AI总结:

本文提出图子结构网络(GSN),通过子结构编码增强消息传递,使 GNN 表达能力严格超越 WL 测试,并在图分类与回归任务中取得最优结果。

摘要:

尽管图神经网络(GNN)在众多应用中取得了显著成果,近期研究却揭示了其在捕捉底层图结构能力方面的重要缺陷。已有研究表明,标准 GNN 的表达能力受限于 Weisfeiler-Leman(WL)图同构测试,并因此继承了已被证明的局限性,例如无法检测和计数图子结构。另一方面,在网络科学与生物信息学等领域存在大量经验证据表明,子结构往往与下游任务密切相关。为此,我们提出“图子结构网络”(Graph Substructure Networks, GSN),这是一种基于子结构编码的拓扑感知消息传递方案。我们从理论上分析了该架构的表达能力,证明其严格强于 WL 测试,并给出了通用性的充分条件。重要的是,我们不试图遵循 WL 层级;这使我们能够保留标准 GNN 的多种优良特性,如局部性和线性网络复杂度,同时能够区分甚至困难的图同构实例。我们在图分类与回归任务上进行了广泛的实验评估,并在包括分子图和社会网络在内的多种真实世界场景中取得了最先进的结果。代码已公开于 https://github.com/gbouritsas/graph-substructure-networks。

英文摘要:

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Leman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures. On the other hand, there is significant empirical evidence, e.g. in network science and bioinformatics, that substructures are often intimately related to downstream tasks. To this end, we propose "Graph Substructure Networks" (GSN), a topologically-aware message passing scheme based on substructure encoding. We theoretically analyse the expressive power of our architecture, showing that it is strictly more expressive than the WL test, and provide sufficient conditions for universality. Importantly, we do not attempt to adhere to the WL hierarchy; this allows us to retain multiple attractive properties of standard GNNs such as locality and linear network complexity, while being able to disambiguate even hard instances of graph isomorphism. We perform an extensive experimental evaluation on graph classification and regression tasks and obtain state-of-the-art results in diverse real-world settings including molecular graphs and social networks. The code is publicly available at https://github.com/gbouritsas/graph-substructure-networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑