Relation-Aware Neighborhood Matching Model for Entity Alignment

• DOI: 10.1609/aaai.v35i5.16606
• Publication Date: 2022-09-08T18:29:05Z
• Authors: Yao Zhu; Hongzhi Liu; Zhonghai Wu; Yingpeng Du
• Keywords: Leverage (statistics); Entity linking; Knowledge graph

Entity alignment which aims at linking entities with the same meaning from different knowledge graphs (KGs) is a vital step for fusion. Existing research focused on learning embeddings of by utilizing structural information KGs entity alignment. These methods can aggregate neighboring nodes but may also bring noise neighbors. Most recently, several researchers attempted to compare in pairs enhance However, they ignored relations between are important neighborhood matching. In addition, existing paid less attention positive interactions and relation To deal these issues, we propose novel Relation-aware Neighborhood Matching model named RNM Specifically, utilize matching Besides comparing neighbor when neighborhood, try explore useful connected relations. Moreover, an iterative framework designed leverage semi-supervised manner. Experimental results three real-world datasets demonstrate that proposed performs better than state-of-the-art methods.