Graph Contrastive Learning under Heterophily via Graph Filters
This addresses a specific bottleneck in graph representation learning for heterophilic graphs, which is incremental but impactful for domains like social or biological networks.
The paper tackles the problem of graph contrastive learning performing poorly on heterophilic graphs, where connected nodes belong to different classes, by proposing HLCL, which uses graph filters to handle homophilic and heterophilic subgraphs, resulting in up to 7% improvement over state-of-the-art graph CL methods and up to 10% over supervised methods on heterophilic datasets.
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%.