A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Yimin, Wu, Yuxia, Wang, Yejing, Zhao, Guoshuai, Zhu, Li, Liu, Qidong, Xu, Derong, Fu, Zichuan, Wu, Xian, Zheng, Yefeng, Zhao, Xiangyu, Qian, Xueming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909651396722688
author Deng, Yimin
Wu, Yuxia
Wang, Yejing
Zhao, Guoshuai
Zhu, Li
Liu, Qidong
Xu, Derong
Fu, Zichuan
Wu, Xian
Zheng, Yefeng
Zhao, Xiangyu
Qian, Xueming
author_facet Deng, Yimin
Wu, Yuxia
Wang, Yejing
Zhao, Guoshuai
Zhu, Li
Liu, Qidong
Xu, Derong
Fu, Zichuan
Wu, Xian
Zheng, Yefeng
Zhao, Xiangyu
Qian, Xueming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14235
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
Deng, Yimin
Wu, Yuxia
Wang, Yejing
Zhao, Guoshuai
Zhu, Li
Liu, Qidong
Xu, Derong
Fu, Zichuan
Wu, Xian
Zheng, Yefeng
Zhao, Xiangyu
Qian, Xueming
Computation and Language
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.
title A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
topic Computation and Language
url https://arxiv.org/abs/2506.14235