Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding

TL;DR

This paper presents a scalable GNN-based method for entity alignment in large knowledge graphs, reducing structural loss through subgraph generation, self-supervised reconstruction, and embedding merging, validated on large datasets.

Contribution

Introduces a novel scalable entity alignment approach combining subgraph generation, self-supervised reconstruction, and embedding merging to improve accuracy in large knowledge graphs.

Findings

Effective on OpenEA benchmark dataset

Successfully applied to large DBpedia dataset

Reduces structural and alignment loss

Abstract

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.