Unifying Post-hoc Explanations of Knowledge Graph Completions

TL;DR

This paper proposes a unified framework for post-hoc explainability in Knowledge Graph Completion, standardizes evaluation protocols, and emphasizes interpretability to improve reproducibility and usefulness of explanations.

Contribution

It introduces a general multi-objective optimization framework to unify existing explainability methods and refines evaluation standards for better reproducibility in KGC explanations.

Findings

Unified explanation framework via multi-objective optimization

Improved evaluation protocols using standard metrics

Highlighting interpretability as key to meaningful explanations

Abstract

Post-hoc explainability for Knowledge Graph Completion (KGC) lacks formalization and consistent evaluations, hindering reproducibility and cross-study comparisons. This paper argues for a unified approach to post-hoc explainability in KGC. First, we propose a general framework to characterize post-hoc explanations via multi-objective optimization, balancing their effectiveness and conciseness. This unifies existing post-hoc explainability algorithms in KGC and the explanations they produce. Next, we suggest and empirically support improved evaluation protocols using popular metrics like Mean Reciprocal Rank and Hits@$k$. Finally, we stress the importance of interpretability as the ability of explanations to address queries meaningful to end-users. By unifying methods and refining evaluation standards, this work aims to make research in KGC explainability more reproducible and impactful.