Saved in:
Bibliographic Details
Main Authors: Liu, Yang, Fang, Huang, Cai, Yunfeng, Sun, Mingming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.03583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909320134787072
author Liu, Yang
Fang, Huang
Cai, Yunfeng
Sun, Mingming
author_facet Liu, Yang
Fang, Huang
Cai, Yunfeng
Sun, Mingming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03583
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MQuinE: a cure for "Z-paradox" in knowledge graph embedding models
Liu, Yang
Fang, Huang
Cai, Yunfeng
Sun, Mingming
Social and Information Networks
Artificial Intelligence
Machine Learning
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.
title MQuinE: a cure for "Z-paradox" in knowledge graph embedding models
topic Social and Information Networks
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.03583