Saved in:
Bibliographic Details
Main Authors: Moon, Sooho, Ko, Yunyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.06296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917130832707584
author Moon, Sooho
Ko, Yunyong
author_facet Moon, Sooho
Ko, Yunyong
contents Knowledge graph completion (KGC) aims to predict missing facts from the observed KG. While a number of KGC models have been studied, the evaluation of KGC still remain underexplored. In this paper, we observe that existing metrics overlook two key perspectives for KGC evaluation: (A1) predictive sharpness -- the degree of strictness in evaluating an individual prediction, and (A2) popularity-bias robustness -- the ability to predict low-popularity entities. Toward reflecting both perspectives, we propose a novel evaluation framework (PROBE), which consists of a rank transformer (RT) estimating the score of each prediction based on a required level of predictive sharpness and a rank aggregator (RA) aggregating all the scores in a popularity-aware manner. Experiments on real-world KGs reveal that existing metrics tend to over- or under-estimate the accuracy of KGC models, whereas PROBE yields a comprehensive understanding of KGC models and reliable evaluation results.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06296
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion
Moon, Sooho
Ko, Yunyong
Artificial Intelligence
Knowledge graph completion (KGC) aims to predict missing facts from the observed KG. While a number of KGC models have been studied, the evaluation of KGC still remain underexplored. In this paper, we observe that existing metrics overlook two key perspectives for KGC evaluation: (A1) predictive sharpness -- the degree of strictness in evaluating an individual prediction, and (A2) popularity-bias robustness -- the ability to predict low-popularity entities. Toward reflecting both perspectives, we propose a novel evaluation framework (PROBE), which consists of a rank transformer (RT) estimating the score of each prediction based on a required level of predictive sharpness and a rank aggregator (RA) aggregating all the scores in a popularity-aware manner. Experiments on real-world KGs reveal that existing metrics tend to over- or under-estimate the accuracy of KGC models, whereas PROBE yields a comprehensive understanding of KGC models and reliable evaluation results.
title How Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion
topic Artificial Intelligence
url https://arxiv.org/abs/2512.06296