TopoGCL: Topological Graph Contrastive Learning

TL;DR

TopoGCL introduces a novel topological contrastive learning framework that leverages higher-order graph substructures and persistence landscapes to improve unsupervised graph classification performance and robustness.

Contribution

It proposes a new topological contrastive mode using extended persistence landscapes, with theoretical stability guarantees, enhancing GCL by capturing latent shape properties of graphs.

Findings

Achieved significant performance gains on 11 out of 12 datasets.

Demonstrated robustness under noisy conditions.

Introduced extended persistence landscapes with stability guarantees.

Abstract

Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant unlabeled information. However, existing GCL approaches largely tend to overlook the important latent information on higher-order graph substructures. We address this limitation by introducing the concepts of topological invariance and extended persistence on graphs to GCL. In particular, we propose a new contrastive mode which targets topological representations of the two augmented views from the same graph, yielded by extracting latent shape properties of the graph at multiple resolutions. Along with the extended topological layer, we introduce a new extended persistence summary, namely, extended persistence landscapes (EPL) and derive its theoretical stability guarantees. Our extensive numerical results on biological, chemical, and social interaction graphs show that the new Topological Graph Contrastive Learning (TopoGCL) model delivers significant performance gains in unsupervised graph classification for 11 out of 12 considered datasets and also exhibits robustness under noisy scenarios.