Advancing rule learning in knowledge graphs with structure-aware graph transformer

Kang Xu

doi:10.1016/j.ipm.2024.103976

Advancing rule learning in knowledge graphs with structure-aware graph transformer

2025-03-01

0

PRE

AI

DOI：10.1016/j.ipm.2024.103976

Original

Original request for help

Save

Abstract

En 中文

In knowledge graphs (KGs), logic rules offer interpretable explanations for predictions and are essential for reasoning on downstream tasks, such as question answering. However, a key challenge remains unresolved: how to effectively encode and utilize the structural features around the head entity to generate the most applicable rules. This paper proposes a structure- aware graph transformer for rule learning, namely Structure-Aware Rule Learning (SARL), which leverages both local and global structural information of the subgraph around the head entity to generate the most suitable rule path. SARL employs a generalized attention mechanism combined with replaceable feature extractors to aggregate local structural information of entities. It then incorporates global structural and relational information to further model the subgraph structure. Finally, a rule decoder utilizes the comprehensive subgraph representation to generate the most appropriate rules. Comprehensive experiments on four real-world knowledge graph datasets reveal that SARL significantly enhances performance and surpasses existing methods in the link prediction task on large-scale KGs, with Hits@1 improvements of 6.5% on UMLS and 4.5% on FB15K-237.

Keywords:

Rule learning

Knowledge graph reasoning

Graph neural networks

Advancing rule learning in knowledge graphs with structure-aware graph transformer

Abstract

Journal

Organization