Unifying Post-hoc Explanations of Knowledge Graph Completions
This work addresses reproducibility and cross-study comparison issues for researchers in KGC explainability, though it is incremental as it unifies and refines existing methods rather than introducing a new paradigm.
The paper tackles the lack of formalization and consistent evaluations in post-hoc explainability for Knowledge Graph Completion (KGC) by proposing a unified framework and improved evaluation protocols, aiming to enhance reproducibility and impact in the field.
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.