MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation

TL;DR

This paper introduces MixupExplainer, a data augmentation method for GNN explanations that addresses distribution shift issues, improving explanation quality on real-world datasets.

Contribution

It proposes a generalized Graph Information Bottleneck and a mixup-based explanation method with theoretical guarantees to enhance GNN interpretability.

Findings

Outperforms existing explanation methods on synthetic datasets

Reduces distribution shift in real-world applications

Provides theoretical guarantees for explanation quality

Abstract

Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. However, their predictions are often not interpretable. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we shed light on the existence of the distribution shifting issue in existing methods, which affects explanation quality, particularly in applications on real-life datasets with tight decision boundaries. To address this issue, we introduce a generalized Graph Information Bottleneck (GIB) form that includes a label-independent graph variable, which is equivalent to the vanilla GIB. Driven by the generalized GIB, we propose a graph mixup method, MixupExplainer, with a theoretical guarantee to resolve the distribution shifting issue. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed mixup approach over existing approaches. We also provide a detailed analysis of how our proposed approach alleviates the distribution shifting issue.