Relational Reflection Entity Alignment

TL;DR

This paper introduces RREA, a novel GNN-based method for entity alignment in knowledge graphs, which uses relational reflection transformations to improve accuracy and explains existing phenomena in GNN architectures.

Contribution

The paper proposes a new relational reflection transformation for GNNs, providing a unified framework for entity alignment and surpassing state-of-the-art performance.

Findings

RREA outperforms existing methods by 5.8%-10.9% on Hits@1.

The unified framework explains counter-intuitive phenomena in GNN-based entity alignment.

Relational reflection transformation effectively captures relation-specific embeddings.

Abstract

Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs. Recently, with the introduction of GNNs into entity alignment, the architectures of recent models have become more and more complicated. We even find two counter-intuitive phenomena within these methods: (1) The standard linear transformation in GNNs is not working well. (2) Many advanced KG embedding models designed for link prediction task perform poorly in entity alignment. In this paper, we abstract existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation. Furthermore, we propose a novel GNNs-based method, Relational Reflection Entity Alignment (RREA). RREA leverages Relational Reflection Transformation to obtain relation specific embeddings for each entity in a more efficient way. The experimental results on real-world datasets show that our model significantly outperforms the state-of-the-art methods, exceeding by 5.8%-10.9% on Hits@1.