Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

TL;DR

This paper introduces MPAIACL, a contrastive learning-based data augmentation method designed to improve graph neural networks' robustness against covariate distribution shifts in out-of-distribution scenarios.

Contribution

It presents a novel contrastive learning approach that leverages latent space information to enhance GNN performance under covariate shift, outperforming existing methods.

Findings

MPAIACL demonstrates strong generalization across multiple OOD datasets.

The method outperforms baseline models in robustness and accuracy.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most out-of-the-box graph neural networks (GNNs) fail to account for covariate shifts. Furthermore, we observe that existing methods aimed at addressing covariate shifts often fail to fully leverage the rich information contained within the latent space. Motivated by the potential of the latent space, we introduce a new method called MPAIACL for More Powerful Adversarial Invariant Augmentation using Contrastive Learning. MPAIACL leverages contrastive learning to unlock the full potential of vector representations by harnessing their intrinsic information. Through extensive experiments, MPAIACL demonstrates its robust generalization and effectiveness, as it performs well compared with other baselines across various public OOD datasets. The code is publicly available at https://github.com/flzeng1/MPAIACL.