Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views

TL;DR

This paper introduces a multiview contrastive learning method with diffusion filters to better capture higher-order structural similarities in heterophilic graphs, improving node representations and downstream task performance.

Contribution

It presents a novel multiview contrastive learning approach that effectively captures higher-order graph structures in heterophilic graphs using diffusion-based augmentations.

Findings

Outperforms baselines on synthetic and real datasets

Achieves up to 16.06% improvement on Cornell

Consistently improves downstream task performance

Abstract

Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction. In such graphs, nodes share structural similarity identified by the equivalence of their connectivity which is implicitly encoded in the form of higher-order hierarchical information in the graphs. The contrastive methods are popular choices for learning the representation of nodes in a graph. However, existing contrastive methods struggle to capture higher-order graph structures. To address this limitation, we propose a novel multiview contrastive learning approach that integrates diffusion filters on graphs. By incorporating multiple graph views as augmentations, our method captures the structural equivalence in heterophilic graphs, enabling the discovery of hidden relationships and similarities not apparent in traditional node representations. Our approach outperforms baselines on synthetic and real structural datasets, surpassing the best baseline by $16.06\%$ on Cornell, $3.27\%$ on Texas, and $8.04\%$ on Wisconsin. Additionally, it consistently achieves superior performance on proximal tasks, demonstrating its effectiveness in uncovering structural information and improving downstream applications.