MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning

TL;DR

MARIO is a model-agnostic framework that enhances out-of-distribution generalization in unsupervised graph contrastive learning by using information bottleneck and invariant principles, achieving state-of-the-art results.

Contribution

It introduces a novel, model-agnostic recipe with two principles to improve OOD robustness in graph contrastive learning, focusing on node-level tasks.

Findings

Achieves state-of-the-art OOD test performance.

Maintains comparable in-distribution performance.

First work on OOD generalization for graph contrastive learning.

Abstract

In this work, we investigate the problem of out-of-distribution (OOD) generalization for unsupervised learning methods on graph data. This scenario is particularly challenging because graph neural networks (GNNs) have been shown to be sensitive to distributional shifts, even when labels are available. To address this challenge, we propose a \underline{M}odel-\underline{A}gnostic \underline{R}ecipe for \underline{I}mproving \underline{O}OD generalizability of unsupervised graph contrastive learning methods, which we refer to as MARIO. MARIO introduces two principles aimed at developing distributional-shift-robust graph contrastive methods to overcome the limitations of existing frameworks: (i) Information Bottleneck (IB) principle for achieving generalizable representations and (ii) Invariant principle that incorporates adversarial data augmentation to obtain invariant representations. To the best of our knowledge, this is the first work that investigates the OOD generalization problem of graph contrastive learning, with a specific focus on node-level tasks. Through extensive experiments, we demonstrate that our method achieves state-of-the-art performance on the OOD test set, while maintaining comparable performance on the in-distribution test set when compared to existing approaches. The source code for our method can be found at: https://github.com/ZhuYun97/MARIO