An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan


Abstract
Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a crucial step for integrating multi-source KGs.For a long time, most researchers have regarded EA as a pure graph representation learning task and focused on improving graph encoders while paying little attention to the decoding process.In this paper, we propose an effective and efficient EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI).Specifically, we derive two sets of isomorphism equations: (1) Adjacency tensor isomorphism equations and (2) Gramian tensor isomorphism equations.By combining these equations, DATTI could effectively utilize the adjacency and inner correlation isomorphisms of KGs to enhance the decoding process of EA.Extensive experiments on public datasets indicate that our decoding algorithm can deliver significant performance improvements even on the most advanced EA methods, while the extra required time is less than 3 seconds.
Anthology ID:
2022.acl-long.405
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5888–5898
Language:
URL:
https://aclanthology.org/2022.acl-long.405
DOI:
10.18653/v1/2022.acl-long.405
Bibkey:
Cite (ACL):
Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, and Man Lan. 2022. An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5888–5898, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (Mao et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.405.pdf
Software:
 2022.acl-long.405.software.zip
Code
 maoxinn/datti