Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
This work addresses scalability issues in entity alignment for knowledge graph fusion, offering incremental improvements over existing partitioning methods.
The paper tackles the scalability problem in entity alignment for knowledge graph fusion by proposing a GNN-based approach that reduces structure and alignment loss through centrality-based subgraph generation, self-supervised entity reconstruction, and cross-subgraph negative sampling, achieving effectiveness verified on benchmark datasets.
Entity alignment is a crucial task in knowledge graph fusion. However, most entity alignment approaches have the scalability problem. Recent methods address this issue by dividing large KGs into small blocks for embedding and alignment learning in each. However, such a partitioning and learning process results in an excessive loss of structure and alignment. Therefore, in this work, we propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives. First, we propose a centrality-based subgraph generation algorithm to recall some landmark entities serving as the bridges between different subgraphs. Second, we introduce self-supervised entity reconstruction to recover entity representations from incomplete neighborhood subgraphs, and design cross-subgraph negative sampling to incorporate entities from other subgraphs in alignment learning. Third, during the inference process, we merge the embeddings of subgraphs to make a single space for alignment search. Experimental results on the benchmark OpenEA dataset and the proposed large DBpedia1M dataset verify the effectiveness of our approach.