Adversarial Graph Contrastive Learning with Information Regularization

TL;DR

This paper introduces ARIEL, a novel adversarial graph contrastive learning method that enhances sample quality and robustness in graph representation learning, outperforming existing methods on node classification tasks.

Contribution

The paper proposes ARIEL, an adversarial graph contrastive learning framework with an information regularizer, improving sample informativeness and robustness over prior graph contrastive methods.

Findings

ARIEL outperforms existing graph contrastive methods on node classification.

ARIEL enhances robustness of graph contrastive learning.

The method effectively extracts informative contrastive samples.

Abstract

Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs. However, most prior works are directly adapted from the models designed for images. Unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which are the key to the performance of contrastive learning models. This leaves much space for improvement over the existing graph contrastive learning frameworks. In this work, by introducing an adversarial graph view and an information regularizer, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within a reasonable constraint. It consistently outperforms the current graph contrastive learning methods in the node classification task over various real-world datasets and further improves the robustness of graph contrastive learning. The code is at https://github.com/Shengyu-Feng/ARIEL.