P-NAL: an Effective and Interpretable Entity Alignment Method

arXiv:2404.11968v1 Announce Type: new
Abstract: Entity alignment (EA) aims to find equivalent entities between two Knowledge Graphs. Existing embedding-based EA methods usually encode entities as embeddings, triples as embeddings' constraint and learn to align the embeddings. The structural and side information are usually utilized via embedding propagation, aggregation or interaction. However, the details of the underlying logical inference steps among the alignment process are usually omitted, resulting in inadequate inference process. In this paper, we introduce P-NAL, an entity alignment …

abstract aggregation alignment arxiv cs.cl embedding embeddings encode graphs however information knowledge knowledge graphs learn propagation type via