eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules

TL;DR

eXpath introduces a path-based explanation framework for knowledge graph link prediction that improves interpretability, efficiency, and semantic meaningfulness by leveraging ontological closed path rules, outperforming existing methods.

Contribution

The paper proposes eXpath, a novel path-based explanation method using ontological closed path rules to enhance interpretability and efficiency in KG link prediction.

Findings

Boosts explanation quality by about 20% on key metrics

Reduces explanation time by 61.4%

Provides more semantically meaningful explanations

Abstract

Link prediction (LP) is crucial for Knowledge Graphs (KG) completion but commonly suffers from interpretability issues. While several methods have been proposed to explain embedding-based LP models, they are generally limited to local explanations on KG and are deficient in providing human interpretable semantics. Based on real-world observations of the characteristics of KGs from multiple domains, we propose to explain LP models in KG with path-based explanations. An integrated framework, namely eXpath, is introduced which incorporates the concept of relation path with ontological closed path rules to enhance both the efficiency and effectiveness of LP interpretation. Notably, the eXpath explanations can be fused with other single-link explanation approaches to achieve a better overall solution. Extensive experiments across benchmark datasets and LP models demonstrate that introducing eXpath can boost the quality of resulting explanations by about 20% on two key metrics and reduce the required explanation time by 61.4%, in comparison to the best existing method. Case studies further highlight eXpath's ability to provide more semantically meaningful explanations through path-based evidence.