HENF: Hierarchical Entity Neighbor Multi-Relational Fusion Network for Knowledge Graph Completion

Knowledge Graph Completion (KGC) aims to predict missing links in a knowledge graph. A popular model for this task is the Graph Neural Network (GNN), which leverages structural information from neighboring nodes. However, current GNN-based methods treat all neighbors equally, overlooking the importance of entity neighbors and handling complex relationships effectively. To address these challenges, we introduce the Hierarchical Entity Neighbor Multi-Relational Fusion Network (HENF) for KGC. HENF offers fine-grained adaptability to various multi-relational scenarios. It constructs relationship subgraphs based on one-hop paths between entities, aggregating information around entities using dynamic attention mechanisms. Furthermore, it employs Adjacent Relation Fusion (ARF) attention to combine rich entity information from different relational graphs. This approach allows our model to emphasize diverse semantic information types under various relations, selectively gather informative features, and assign appropriate weights. Extensive experiments demonstrate that HENF significantly enhances KGC performance, especially on datasets with many-to-many relationships.