Cross-View Topology-Aware Graph Representation Learning

TL;DR

This paper introduces GraphTCL, a dual-view contrastive learning framework that combines GNN-based structural embeddings with topological features from persistent homology, leading to improved graph classification performance.

Contribution

The paper presents a novel topology-aware contrastive learning approach that integrates local and global graph features for enhanced representation learning.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively combines structural and topological features

Improves robustness and accuracy in graph classification

Abstract

Graph classification has gained significant attention due to its applications in chemistry, social networks, and bioinformatics. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they often overlook global topological features that are critical for robust representation learning. In this work, we propose GraphTCL, a dual-view contrastive learning framework that integrates structural embeddings from GNNs with topological embeddings derived from persistent homology. By aligning these complementary views through a cross-view contrastive loss, our method enhances representation quality and improves classification performance. Extensive experiments on benchmark datasets, including TU and OGB molecular graphs, demonstrate that GraphTCL consistently outperforms state-of-the-art baselines. This study highlights the importance of topology-aware contrastive learning for advancing graph representation methods.