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

TL;DR

This paper introduces a Multi-Expert Structural-Semantic Hybrid framework for temporal knowledge graph reasoning, effectively integrating structural and semantic reasoning to improve prediction of historical and non-historical events.

Contribution

The proposed MESH framework uniquely combines multiple expert modules for dual reasoning, addressing limitations of prior methods in handling diverse temporal scenarios.

Findings

Outperforms existing methods on three datasets

Effectively captures differences between historical and non-historical events

Demonstrates improved reasoning accuracy in temporal knowledge graphs

Abstract

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.