Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer

TL;DR

This paper introduces RPR-RHGT, a novel entity alignment framework that leverages reliable path reasoning and relation-aware heterogeneous graph transformers to improve accuracy in aligning entities across knowledge graphs.

Contribution

It presents the first reliable path reasoning algorithm for EA and a relation-aware heterogeneous graph transformer to effectively utilize heterogeneous KG information.

Findings

RPR-RHGT outperforms 11 state-of-the-art methods by up to 8.62% on Hits@1.

The method performs well across different training ratios and more challenging datasets.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Entity Alignment (EA) has attracted widespread attention in both academia and industry, which aims to seek entities with same meanings from different Knowledge Graphs (KGs). There are substantial multi-step relation paths between entities in KGs, indicating the semantic relations of entities. However, existing methods rarely consider path information because not all natural paths facilitate for EA judgment. In this paper, we propose a more effective entity alignment framework, RPR-RHGT, which integrates relation and path structure information, as well as the heterogeneous information in KGs. Impressively, an initial reliable path reasoning algorithm is developed to generate the paths favorable for EA task from the relation structures of KGs, which is the first algorithm in the literature to successfully use unrestricted path information. In addition, to efficiently capture heterogeneous features in entity neighborhoods, a relation-aware heterogeneous graph transformer is designed to model the relation and path structures of KGs. Extensive experiments on three well-known datasets show RPR-RHGT significantly outperforms 11 state-of-the-art methods, exceeding the best performing baseline up to 8.62% on Hits@1. We also show its better performance than the baselines on different ratios of training set, and harder datasets.