arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01635cs.LGcs.AI
收藏

通勤图神经网络

Commute Graph Neural Networks

Nanyang Technological University(南洋理工大学);The University of British Columbia(不列颠哥伦比亚大学);Vector Institute(向量研究所)

Wei Zhuo, Han Yu, Guang Tan, Xiaoxiao Li

AI总结:

针对有向图关系非对称导致传统 GNN 难以编码相互路径依赖的问题,提出 CGNN,利用新型有向图 Laplacian 计算通勤时间并加权邻域聚合,在 8 个基准上优于 13 种方法。

摘要:

图神经网络(GNN)在从图结构数据中学习方面已取得显著成功。然而,将其应用于有向图(digraph)时面临独特挑战,主要原因在于节点关系固有的非对称性。传统 GNN 擅长捕捉单向关系,但难以编码节点之间的相互路径依赖,例如有向图中常见的非对称最短路径。认识到这一空白,我们提出通勤图神经网络(Commute Graph Neural Networks,CGNN),该方法将逐节点通勤时间无缝集成到消息传递机制中。CGNN 的基石是利用新构建的有向图 Laplacian 高效计算通勤时间的方法。随后,通勤时间被融入邻域聚合过程,在每一层中根据各邻居到中心节点的相应通勤时间对邻居贡献进行加权。这使 CGNN 能够直接捕捉有向图中相互且非对称的关系。在 8 个基准数据集上进行的大量实验证实,CGNN 优于 13 种最先进方法。

英文摘要:

Graph Neural Networks (GNNs) have shown remarkable success in learning from graph-structured data. However, their application to directed graphs (digraphs) presents unique challenges, primarily due to the inherent asymmetry in node relationships. Traditional GNNs are adept at capturing unidirectional relations but fall short in encoding the mutual path dependencies between nodes, such as asymmetrical shortest paths typically found in digraphs. Recognizing this gap, we introduce Commute Graph Neural Networks (CGNN), an approach that seamlessly integrates node-wise commute time into the message passing scheme. The cornerstone of CGNN is an efficient method for computing commute time using a newly formulated digraph Laplacian. Commute time is then integrated into the neighborhood aggregation process, with neighbor contributions weighted according to their respective commute time to the central node in each layer. It enables CGNN to directly capture the mutual, asymmetric relationships in digraphs. Extensive experiments on 8 benchmarking datasets confirm the superiority of CGNN against 13 state-of-the-art methods.

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。

↑