Path-based Explanation for Knowledge Graph Completion

TL;DR

This paper introduces Power-Link, a novel path-based explanation method for GNN-based Knowledge Graph Completion that improves interpretability, efficiency, and scalability through a new graph-powering technique and comprehensive evaluation.

Contribution

Power-Link is the first path-based explainer for GNNs in KGC, offering a parallelisable and memory-efficient approach with new evaluation metrics.

Findings

Power-Link outperforms state-of-the-art methods in interpretability.

It demonstrates superior efficiency and scalability.

Qualitative human evaluation confirms explanation quality.

Abstract

Graph Neural Networks (GNNs) have achieved great success in Knowledge Graph Completion (KGC) by modelling how entities and relations interact in recent years. However, the explanation of the predicted facts has not caught the necessary attention. Proper explanations for the results of GNN-based KGC models increase model transparency and help researchers develop more reliable models. Existing practices for explaining KGC tasks rely on instance/subgraph-based approaches, while in some scenarios, paths can provide more user-friendly and interpretable explanations. Nonetheless, the methods for generating path-based explanations for KGs have not been well-explored. To address this gap, we propose Power-Link, the first path-based KGC explainer that explores GNN-based models. We design a novel simplified graph-powering technique, which enables the generation of path-based explanations with a fully parallelisable and memory-efficient training scheme. We further introduce three new metrics for quantitative evaluation of the explanations, together with a qualitative human evaluation. Extensive experiments demonstrate that Power-Link outperforms the SOTA baselines in interpretability, efficiency, and scalability.