Graph Contrastive Learning with Augmentations

TL;DR

This paper introduces GraphCL, a framework for unsupervised graph representation learning using diverse augmentations, demonstrating improved generalizability, transferability, and robustness across various tasks and settings.

Contribution

It proposes four novel graph augmentation techniques and systematically studies their effects, establishing a simple yet effective contrastive learning framework for graphs.

Findings

GraphCL achieves comparable or better performance than state-of-the-art methods.

Augmentation strategies significantly impact the quality of learned representations.

Parameter tuning of augmentations yields further improvements.

Abstract

Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augmentations on multiple datasets, in four different settings: semi-supervised, unsupervised, and transfer learning as well as adversarial attacks. The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, our GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. We also investigate the impact of parameterized graph augmentation extents and patterns, and observe further performance gains in preliminary experiments. Our codes are available at https://github.com/Shen-Lab/GraphCL.