MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding

Yang Liu, Huang Fang, Yunfeng Cai, Mingming Sun


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 Z-paradox. Motivated by the existence of Z-paradox, we propose a new KGE model called 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.
Anthology ID:
2024.emnlp-main.549
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9837–9850
Language:
URL:
https://aclanthology.org/2024.emnlp-main.549
DOI:
10.18653/v1/2024.emnlp-main.549
Bibkey:
Cite (ACL):
Yang Liu, Huang Fang, Yunfeng Cai, and Mingming Sun. 2024. MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9837–9850, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding (Liu et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.emnlp-main.549.pdf