Towards Effective Graph Rationalization via Boosting Environment Diversity

TL;DR

This paper introduces GRBE, a novel graph rationalization method that enhances environment diversity by generating augmented samples directly in the original graph space, improving GNN generalization under distribution shifts.

Contribution

GRBE proposes a new approach for graph rationalization that refines rationale extraction and diversifies environment subgraphs in the original graph space, outperforming existing methods.

Findings

Achieves 7.65% improvement in rationalization performance

Achieves 6.11% improvement in classification accuracy

Demonstrates superiority over state-of-the-art approaches

Abstract

Graph Neural Networks (GNNs) perform effectively when training and testing graphs are drawn from the same distribution, but struggle to generalize well in the face of distribution shifts. To address this issue, existing mainstreaming graph rationalization methods first identify rationale and environment subgraphs from input graphs, and then diversify training distributions by augmenting the environment subgraphs. However, these methods merely combine the learned rationale subgraphs with environment subgraphs in the representation space to produce augmentation samples, failing to produce sufficiently diverse distributions. Thus, in this paper, we propose to achieve an effective Graph Rationalization by Boosting Environmental diversity, a GRBE approach that generates the augmented samples in the original graph space to improve the diversity of the environment subgraph. Firstly, to ensure the effectiveness of augmentation samples, we propose a precise rationale subgraph extraction strategy in GRBE to refine the rationale subgraph learning process in the original graph space. Secondly, to ensure the diversity of augmented samples, we propose an environment diversity augmentation strategy in GRBE that mixes the environment subgraphs of different graphs in the original graph space and then combines the new environment subgraphs with rationale subgraphs to generate augmented graphs. The average improvements of 7.65% and 6.11% in rationalization and classification performance on benchmark datasets demonstrate the superiority of GRBE over state-of-the-art approaches.