arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06835cs.LG
收藏

通过有效电阻视角理解 GNN 中的过度挤压

Understanding Oversquashing in GNNs through the Lens of Effective Resistance

Oregon State University(俄勒冈州立大学);University of California San Diego(加利福尼亚大学圣迭戈分校)

Mitchell Black, Zhengchao Wan, Amir Nayyeri, Yusu Wang

AI总结:

本文以节点间有效电阻刻画 GNN 的过度挤压,提出用总有效电阻界定挤压程度,并设计边添加算法最小化该指标,从而通过图重连提升 GNN 性能。

摘要:

消息传递图神经网络(GNN)是用于图结构数据的流行学习架构。然而,GNN 面临的一个问题是过度挤压,即 GNN 难以在远距离节点之间传递信息。近年来,理解和缓解过度挤压受到了研究界的广泛关注。本文延续这一研究方向,通过输入图中节点之间的有效电阻来分析过度挤压。有效电阻直观地刻画了两个节点经由图中路径建立连接的“强度”,并在图论众多领域拥有丰富的研究文献。我们提出使用总有效电阻作为图中过度挤压总量的界,并为其使用提供理论依据。我们进一步开发了一种算法,用于识别应添加到输入图中的边,以最小化总有效电阻,从而缓解过度挤压。我们提供了实证证据,表明基于总有效电阻的重连策略能够有效提升 GNN 的性能。

英文摘要:

Message passing graph neural networks (GNNs) are a popular learning architectures for graph-structured data. However, one problem GNNs experience is oversquashing, where a GNN has difficulty sending information between distant nodes. Understanding and mitigating oversquashing has recently received significant attention from the research community. In this paper, we continue this line of work by analyzing oversquashing through the lens of the effective resistance between nodes in the input graph. Effective resistance intuitively captures the ``strength'' of connection between two nodes by paths in the graph, and has a rich literature spanning many areas of graph theory. We propose to use total effective resistance as a bound of the total amount of oversquashing in a graph and provide theoretical justification for its use. We further develop an algorithm to identify edges to be added to an input graph to minimize the total effective resistance, thereby alleviating oversquashing. We provide empirical evidence of the effectiveness of our total effective resistance based rewiring strategies for improving the performance of GNNs.

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。

↑