Dual Relation-Aware Entity Alignment for Knowledge Graph

Entity alignment (EA) is a vital step for knowledge fusion, which aims to discover entities with the same meaning from the different knowledge graphs. Several researchers attempted to obtain enhanced entity embeddings by using the strategies that relation-aware entity embeddings for EA. However, they ignored the effect of aggregating different range neighborhoods of entities on relation embeddings. In this study, we propose a novel Dual Relation-aware Entity Alignment framework named DRAEA for EA. Specifically, we utilize entity embeddings based on 1-hop neighborhoods and 2-hop neighborhoods to represent different relation embeddings, respectively. Then we aggregate different relation embeddings back to entity embeddings by using the self-attention mechanism. Last, an effective entity-assisted global alignment strategy is designed to accomplish the EA tasks. Experimental results on three real-world datasets show that DRAEA outperforms the state-of-the-art methods.