English

MQuinE: a cure for "Z-paradox" in knowledge graph embedding models

Social and Information Networks 2024-09-23 v3 Artificial Intelligence Machine Learning

Abstract

Knowledge graph embedding (KGE) models achieved state-of-the-art results on many knowledge graph tasks including link prediction and information retrieval. Despite the superior performance of KGE models in practice, we discover a deficiency in the expressiveness of some popular existing KGE models called \emph{Z-paradox}. Motivated by the existence of Z-paradox, we propose a new KGE model called \emph{MQuinE} that does not suffer from Z-paradox while preserves strong expressiveness to model various relation patterns including symmetric/asymmetric, inverse, 1-N/N-1/N-N, and composition relations with theoretical justification. Experiments on real-world knowledge bases indicate that Z-paradox indeed degrades the performance of existing KGE models, and can cause more than 20\% accuracy drop on some challenging test samples. Our experiments further demonstrate that MQuinE can mitigate the negative impact of Z-paradox and outperform existing KGE models by a visible margin on link prediction tasks.

Keywords

Cite

@article{arxiv.2402.03583,
  title  = {MQuinE: a cure for "Z-paradox" in knowledge graph embedding models},
  author = {Yang Liu and Huang Fang and Yunfeng Cai and Mingming Sun},
  journal= {arXiv preprint arXiv:2402.03583},
  year   = {2024}
}

Comments

18pages, 1 figure

R2 v1 2026-06-28T14:39:27.326Z