Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Yuqicheng, Potyka, Nico, Nayyeri, Mojtaba, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny, Staab, Steffen
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913531576713216
author Zhu, Yuqicheng
Potyka, Nico
Nayyeri, Mojtaba
Xiong, Bo
He, Yunjie
Kharlamov, Evgeny
Staab, Steffen
author_facet Zhu, Yuqicheng
Potyka, Nico
Nayyeri, Mojtaba
Xiong, Bo
He, Yunjie
Kharlamov, Evgeny
Staab, Steffen
contents Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet give conflicting predictions for unseen queries. This phenomenon is termed \textit{predictive multiplicity} in the literature. It poses substantial risks for KGE-based applications in high-stake domains but has been overlooked in KGE research. We define predictive multiplicity in link prediction, introduce evaluation metrics and measure predictive multiplicity for representative KGE methods on commonly used benchmark datasets. Our empirical study reveals significant predictive multiplicity in link prediction, with $8\%$ to $39\%$ testing queries exhibiting conflicting predictions. We address this issue by leveraging voting methods from social choice theory, significantly mitigating conflicts by $66\%$ to $78\%$ in our experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08226
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction
Zhu, Yuqicheng
Potyka, Nico
Nayyeri, Mojtaba
Xiong, Bo
He, Yunjie
Kharlamov, Evgeny
Staab, Steffen
Artificial Intelligence
Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet give conflicting predictions for unseen queries. This phenomenon is termed \textit{predictive multiplicity} in the literature. It poses substantial risks for KGE-based applications in high-stake domains but has been overlooked in KGE research. We define predictive multiplicity in link prediction, introduce evaluation metrics and measure predictive multiplicity for representative KGE methods on commonly used benchmark datasets. Our empirical study reveals significant predictive multiplicity in link prediction, with $8\%$ to $39\%$ testing queries exhibiting conflicting predictions. We address this issue by leveraging voting methods from social choice theory, significantly mitigating conflicts by $66\%$ to $78\%$ in our experiments.
title Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2408.08226