Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization

TL;DR

This paper introduces a novel method to improve distribution and label consistency in graph out-of-distribution generalization, leading to better robustness by generating more realistic augmented graphs and preserving label relationships.

Contribution

The proposed approach unifies augmentation and invariant graph generation to enhance both distribution and label consistency in graph OOD generalization.

Findings

Outperforms state-of-the-art baselines on real-world datasets.

Improves robustness by maintaining label-graph relationships.

Enhances generalization under distribution shifts.

Abstract

To deal with distribution shifts in graph data, various graph out-of-distribution (OOD) generalization techniques have been recently proposed. These methods often employ a two-step strategy that first creates augmented environments and subsequently identifies invariant subgraphs to improve generalizability. Nevertheless, this approach could be suboptimal from the perspective of consistency. First, the process of augmenting environments by altering the graphs while preserving labels may lead to graphs that are not realistic or meaningfully related to the origin distribution, thus lacking distribution consistency. Second, the extracted subgraphs are obtained from directly modifying graphs, and may not necessarily maintain a consistent predictive relationship with their labels, thereby impacting label consistency. In response to these challenges, we introduce an innovative approach that aims to enhance these two types of consistency for graph OOD generalization. We propose a modifier to obtain both augmented and invariant graphs in a unified manner. With the augmented graphs, we enrich the training data without compromising the integrity of label-graph relationships. The label consistency enhancement in our framework further preserves the supervision information in the invariant graph. We conduct extensive experiments on real-world datasets to demonstrate the superiority of our framework over other state-of-the-art baselines.