TopoGCL: Topological Graph Contrastive Learning
This work addresses the problem of learning rich graph representations for applications like biological, chemical, and social interaction graphs, offering a novel approach that is incremental but delivers strong specific gains.
The paper tackles the limitation of existing graph contrastive learning methods by incorporating topological invariance and extended persistence to capture higher-order graph substructures, resulting in significant performance gains in unsupervised graph classification for 11 out of 12 datasets and improved robustness under noise.
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.