A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning

TL;DR

FOSSIL introduces a novel contrastive learning method that fuses Gromov-Wasserstein distance with node and subgraph-level learning, improving graph representations especially in diverse graph types.

Contribution

The paper proposes FOSSIL, a new self-supervised graph learning approach that effectively combines structural and feature information using a fused Gromov-Wasserstein framework.

Findings

FOSSIL outperforms current state-of-the-art methods on benchmark datasets.

The method is effective for both homophilic and heterophilic graphs.

FOSSIL demonstrates strong generalization across various graph tasks.

Abstract

Self-supervised learning has become a key method for training deep learning models when labeled data is scarce or unavailable. While graph machine learning holds great promise across various domains, the design of effective pretext tasks for self-supervised graph representation learning remains challenging. Contrastive learning, a popular approach in graph self-supervised learning, leverages positive and negative pairs to compute a contrastive loss function. However, current graph contrastive learning methods often struggle to fully use structural patterns and node similarities. To address these issues, we present a new method called Fused Gromov Wasserstein Subgraph Contrastive Learning (FOSSIL). Our model integrates node-level and subgraph-level contrastive learning, seamlessly combining a standard node-level contrastive loss with the Fused Gromov-Wasserstein distance. This combination helps our method capture both node features and graph structure together. Importantly, our approach works well with both homophilic and heterophilic graphs and can dynamically create views for generating positive and negative pairs. Through extensive experiments on benchmark graph datasets, we show that FOSSIL outperforms or achieves competitive performance compared to current state-of-the-art methods.