Learning Robust Representation through Graph Adversarial Contrastive Learning

TL;DR

This paper introduces GraphACL, a novel framework that enhances the robustness of graph neural network representations against adversarial attacks by using adversarial augmentations and mutual information maximization.

Contribution

It proposes a new adversarial contrastive learning approach for graphs, with theoretical proof of improved robustness based on the Information Bottleneck Principle.

Findings

Achieves comparable accuracy to supervised methods on node classification benchmarks.

Demonstrates increased robustness of graph representations against adversarial perturbations.

Validates effectiveness through extensive empirical evaluations.

Abstract

Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features. Thus, it is requisite to learn robust representations in graph neural networks. To improve the robustness of graph representation learning, we propose a novel Graph Adversarial Contrastive Learning framework (GraphACL) by introducing adversarial augmentations into graph self-supervised learning. In this framework, we maximize the mutual information between local and global representations of a perturbed graph and its adversarial augmentations, where the adversarial graphs can be generated in either supervised or unsupervised approaches. Based on the Information Bottleneck Principle, we theoretically prove that our method could obtain a much tighter bound, thus improving the robustness of graph representation learning. Empirically, we evaluate several methods on a range of node classification benchmarks and the results demonstrate GraphACL could achieve comparable accuracy over previous supervised methods.