MUSE: Integrating Multi-Knowledge for Knowledge Graph Completion

TL;DR

MUSE is a novel knowledge graph completion model that integrates multiple knowledge sources and external semantic information to improve missing relation prediction, outperforming existing methods on several datasets.

Contribution

The paper introduces MUSE, a multi-knowledge representation learning model that combines prior knowledge, context message passing, and relational path aggregation for enhanced KGC.

Findings

Achieves over 5.50% H@1 improvement on NELL995

Outperforms baselines on four datasets

Significantly improves relation prediction accuracy

Abstract

Knowledge Graph Completion (KGC) aims to predict the missing [relation] part of (head entity)--[relation]->(tail entity) triplet. Most existing KGC methods focus on single features (e.g., relation types) or sub-graph aggregation. However, they do not fully explore the Knowledge Graph (KG) features and neglect the guidance of external semantic knowledge. To address these shortcomings, we propose a knowledge-aware reasoning model (MUSE), which designs a novel multi-knowledge representation learning mechanism for missing relation prediction. Our model develops a tailored embedding space through three parallel components: 1) Prior Knowledge Learning for enhancing the triplets' semantic representation by fine-tuning BERT; 2) Context Message Passing for enhancing the context messages of KG; 3) Relational Path Aggregation for enhancing the path representation from the head entity to the tail entity. The experimental results show that MUSE significantly outperforms other baselines on four public datasets, achieving over 5.50% H@1 improvement and 4.20% MRR improvement on the NELL995 dataset. The code and datasets will be released via https://github.com/SUSTech-TP/ADMA2024-MUSE.git.