MUSE: Multi-View Contrastive Learning for Heterophilic Graphs

TL;DR

MUSE introduces a multi-view contrastive learning framework for heterophilic graphs, effectively capturing diverse node and neighborhood information to improve node classification and clustering performance.

Contribution

This work presents a novel multi-view contrastive learning model with an information fusion controller tailored for heterophilic graphs, addressing limitations of existing methods.

Findings

Outperforms existing methods on 9 benchmark datasets

Improves node classification accuracy in heterophilic graphs

Enhances clustering quality of node representations

Abstract

In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited effectiveness on heterophilic graphs, due to the homophily assumption that results in similar node representations for connected nodes. In this work, we propose a multi-view contrastive learning model for heterophilic graphs, namely, MUSE. Specifically, we construct two views to capture the information of the ego node and its neighborhood by GNNs enhanced with contrastive learning, respectively. Then we integrate the information from these two views to fuse the node representations. Fusion contrast is utilized to enhance the effectiveness of fused node representations. Further, considering that the influence of neighboring contextual information on information fusion may vary across different ego nodes, we employ an information fusion controller to model the diversity of node-neighborhood similarity at both the local and global levels. Finally, an alternating training scheme is adopted to ensure that unsupervised node representation learning and information fusion controller can mutually reinforce each other. We conduct extensive experiments to evaluate the performance of MUSE on 9 benchmark datasets. Our results show the effectiveness of MUSE on both node classification and clustering tasks.