RAW-Explainer: Post-hoc Explanations of Graph Neural Networks on Knowledge Graphs

TL;DR

RAW-Explainer is a new neural network-based framework that generates concise, connected subgraph explanations for link predictions in knowledge graphs, addressing interpretability and efficiency challenges.

Contribution

It introduces a novel, fast, and robust method for generating interpretable subgraph explanations for GNN link predictions on knowledge graphs.

Findings

Balances explanation quality and computational efficiency

Outperforms existing methods in real-world datasets

Addresses distribution shift in explanation evaluation

Abstract

Graph neural networks have demonstrated state-of-the-art performance on knowledge graph tasks such as link prediction. However, interpreting GNN predictions remains a challenging open problem. While many GNN explainability methods have been proposed for node or graph-level tasks, approaches for generating explanations for link predictions in heterogeneous settings are limited. In this paper, we propose RAW-Explainer, a novel framework designed to generate connected, concise, and thus interpretable subgraph explanations for link prediction. Our method leverages the heterogeneous information in knowledge graphs to identify connected subgraphs that serve as patterns of factual explanation via a random walk objective. Unlike existing methods tailored to knowledge graphs, our approach employs a neural network to parameterize the explanation generation process, which significantly speeds up the production of collective explanations. Furthermore, RAW-Explainer is designed to overcome the distribution shift issue when evaluating the quality of an explanatory subgraph which is orders of magnitude smaller than the full graph, by proposing a robust evaluator that generalizes to the subgraph distribution. Extensive quantitative results on real-world knowledge graph datasets demonstrate that our approach strikes a balance between explanation quality and computational efficiency.