TY - GEN
T1 - A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
AU - Deng, Yimin
AU - Wu, Yuxia
AU - Wang, Yejing
AU - Zhao, Guoshuai
AU - Zhu, Li
AU - Liu, Qidong
AU - Xu, Derong
AU - Fu, Zichuan
AU - Wu, Xian
AU - Zheng, Yefeng
AU - Zhao, Xiangyu
AU - Qian, Xueming
N1 - Publisher Copyright:
© 2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - Temporal knowledge graph reasoning aims to predict future events with knowledge of existing facts and plays a key role in various downstream tasks. Previous methods focused on either graph structure learning or semantic reasoning, failing to integrate dual reasoning perspectives to handle different prediction scenarios. Moreover, they lack the capability to capture the inherent differences between historical and non-historical events, which limits their generalization across different temporal contexts. To this end, we propose a Multi-Expert Structural-Semantic Hybrid (MESH) framework that employs three kinds of expert modules to integrate both structural and semantic information, guiding the reasoning process for different events. Extensive experiments on three datasets demonstrate the effectiveness of our approach.
AB - Temporal knowledge graph reasoning aims to predict future events with knowledge of existing facts and plays a key role in various downstream tasks. Previous methods focused on either graph structure learning or semantic reasoning, failing to integrate dual reasoning perspectives to handle different prediction scenarios. Moreover, they lack the capability to capture the inherent differences between historical and non-historical events, which limits their generalization across different temporal contexts. To this end, we propose a Multi-Expert Structural-Semantic Hybrid (MESH) framework that employs three kinds of expert modules to integrate both structural and semantic information, guiding the reasoning process for different events. Extensive experiments on three datasets demonstrate the effectiveness of our approach.
UR - https://www.scopus.com/pages/publications/105028559011
U2 - 10.18653/v1/2025.findings-acl.1056
DO - 10.18653/v1/2025.findings-acl.1056
M3 - 会议稿件
AN - SCOPUS:105028559011
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 20553
EP - 20565
BT - Findings of the Association for Computational Linguistics
A2 - Che, Wanxiang
A2 - Nabende, Joyce
A2 - Shutova, Ekaterina
A2 - Pilehvar, Mohammad Taher
PB - Association for Computational Linguistics (ACL)
T2 - 63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Y2 - 27 July 2025 through 1 August 2025
ER -