Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift

TL;DR

This paper introduces a novel score-based conditional graph augmentation method to improve out-of-distribution generalization in graph learning by synthesizing unseen environments while preserving stable features.

Contribution

We propose a new distributional augmentation approach using score-based conditional graph generation to explore unseen environments beyond training data.

Findings

Enhanced OOD generalization performance in graph learning tasks.

Outperforms existing augmentation methods in empirical evaluations.

Successfully synthesizes unseen environments while maintaining graph validity.

Abstract

Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally associated with labels, whereas varying environmental features lead to distribution shifts. In particular, covariate shifts caused by unseen environments in test graphs underscore the critical need for out-of-distribution (OOD) generalization. Existing graph augmentation methods designed to address the covariate shift often disentangle the stable and environmental features in the input space, and selectively perturb or mixup the environmental features. However, such perturbation-based methods heavily rely on an accurate separation of stable and environmental features, and their exploration ability is confined to existing environmental features in the training distribution. To overcome these limitations, we introduce a novel distributional augmentation approach enabled by a tailored score-based conditional graph generation strategies to explore and synthesize unseen environments while preserving the validity and stable features of overall graph patterns. Our comprehensive empirical evaluations demonstrate the enhanced effectiveness of our method in improving graph OOD generalization.