Unifying Post-hoc Explanations of Knowledge Graph Completions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lonardi, Alessandro, Badreddine, Samy, Besold, Tarek R., Martin, Pablo Sanchez
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913967148892160
author Lonardi, Alessandro
Badreddine, Samy
Besold, Tarek R.
Martin, Pablo Sanchez
author_facet Lonardi, Alessandro
Badreddine, Samy
Besold, Tarek R.
Martin, Pablo Sanchez
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22951
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unifying Post-hoc Explanations of Knowledge Graph Completions
Lonardi, Alessandro
Badreddine, Samy
Besold, Tarek R.
Martin, Pablo Sanchez
Artificial Intelligence
Machine Learning
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.
title Unifying Post-hoc Explanations of Knowledge Graph Completions
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.22951