Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

arXiv2301.12929MaRDI QIDQ6424817

Author name not available (Why is that?)

Publication date: 30 January 2023

Abstract: In this paper we present a novel method, $extitKnowledgePersistence$ ($mathcalKP$), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-based evaluation is quadratic in the size of the KG, leading to long evaluation times and consequently a high carbon footprint. $mathcalKP$ addresses this by representing the topology of the KG completion methods through the lens of topological data analysis, concretely using persistent homology. The characteristics of persistent homology allow $mathcalKP$ to evaluate the quality of the KG completion looking only at a fraction of the data. Experimental results on standard datasets show that the proposed metric is highly correlated with ranking metrics (Hits@N, MR, MRR). Performance evaluation shows that $mathcalKP$ is computationally efficient: In some cases, the evaluation time (validation+test) of a KG completion method has been reduced from 18 hours (using Hits@10) to 27 seconds (using $mathcalKP$), and on average (across methods & data) reduces the evaluation time (validation+test) by $approx$ $extbf99.96\mathrm{\%}$.

Has companion code repository: https://github.com/ansonb/knowledge_persistence

This page was built for publication: Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6424817)