SubGraph Networks based Entity Alignment for Cross-lingual Knowledge Graph

TL;DR

This paper proposes a novel subgraph network approach integrated with GCNs to improve cross-lingual knowledge graph entity alignment by capturing richer structural features, leading to better alignment accuracy.

Contribution

It introduces the use of first-order subgraphs in GCN-based entity alignment, enhancing structural feature extraction for cross-lingual KGs.

Findings

Outperforms state-of-the-art GCN-based methods

Enhances structural feature representation

Improves alignment accuracy

Abstract

Entity alignment is the task of finding entities representing the same real-world object in two knowledge graphs(KGs). Cross-lingual knowledge graph entity alignment aims to discover the cross-lingual links in the multi-language KGs, which is of great significance to the NLP applications and multi-language KGs fusion. In the task of aligning cross-language knowledge graphs, the structures of the two graphs are very similar, and the equivalent entities often have the same subgraph structure characteristics. The traditional GCN method neglects to obtain structural features through representative parts of the original graph and the use of adjacency matrix is not enough to effectively represent the structural features of the graph. In this paper, we introduce the subgraph network (SGN) method into the GCN-based cross-lingual KG entity alignment method. In the method, we extracted the first-order subgraphs of the KGs to expand the structural features of the original graph to enhance the representation ability of the entity embedding and improve the alignment accuracy. Experiments show that the proposed method outperforms the state-of-the-art GCN-based method.