Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction

TL;DR

This paper investigates the phenomenon of predictive multiplicity in knowledge graph embeddings, revealing that multiple models can produce conflicting predictions for the same query, which poses risks for high-stakes applications.

Contribution

It defines predictive multiplicity in link prediction, introduces evaluation metrics, measures its extent across models, and proposes voting methods to mitigate conflicts.

Findings

Significant predictive multiplicity found, with 8-39% of queries conflicting.

Voting methods reduce conflicts by 66-78%.

Empirical evidence on benchmark datasets supports the analysis.

Abstract

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.