arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.06344cs.LG
收藏

基于图滤波器的异配性下图对比学习

Graph Contrastive Learning under Heterophily via Graph Filters

University of California Los Angeles (UCLA)(加州大学洛杉矶分校)

Wenhan Yang, Baharan Mirzasoleiman

AI总结:

本文提出异配性下图对比学习方法HLCL,通过余弦相似度识别同配与异配子图,并利用低通和高通图滤波器分别聚合与区分节点表示,在多个基准和真实世界图上显著超越现有方法。

摘要:

图对比学习方法通过最大化基于GNN编码器获得的增强节点表示之间的相似性,以自监督方式学习节点表示。然而,对比学习方法在异配性图上表现不佳,在异配性图中,相连节点往往属于不同类别。在本工作中,我们通过提出一种有效的图对比学习方法HLCL来解决该问题,用于在异配性下学习图表示。HLCL首先基于节点特征的余弦相似度识别一个同配子图和一个异配子图。然后,它使用低通和高通图滤波器来聚合同配子图中相连节点的表示,并区分异配子图中节点的表示。最终的节点表示通过对比增强的高通滤波视图和增强的低通滤波节点视图来学习。我们的大量实验表明,HLCL在具有异配性的基准数据集以及大规模真实世界图上,比最先进的图对比学习方法性能提升高达7%,并且在具有异配性的数据集上比图监督学习方法性能提升高达10%。

英文摘要:

Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on graphs with heterophily, where connected nodes tend to belong to different classes. In this work, we address this problem by proposing an effective graph CL method, namely HLCL, for learning graph representations under heterophily. HLCL first identifies a homophilic and a heterophilic subgraph based on the cosine similarity of node features. It then uses a low-pass and a high-pass graph filter to aggregate representations of nodes connected in the homophilic subgraph and differentiate representations of nodes in the heterophilic subgraph. The final node representations are learned by contrasting both the augmented high-pass filtered views and the augmented low-pass filtered node views. Our extensive experiments show that HLCL outperforms state-of-the-art graph CL methods on benchmark datasets with heterophily, as well as large-scale real-world graphs, by up to 7%, and outperforms graph supervised learning methods on datasets with heterophily by up to 10%.

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。

↑