LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation

TL;DR

LightEA is a scalable, robust, and interpretable entity alignment framework that leverages label propagation with three innovative components, outperforming many neural network-based methods in efficiency and effectiveness.

Contribution

We introduce LightEA, a non-neural entity alignment framework utilizing three-view label propagation, addressing scalability and interpretability issues of existing GNN-based methods.

Findings

LightEA achieves comparable or better accuracy than state-of-the-art methods.

It significantly reduces computation time, enhancing scalability.

The framework demonstrates strong robustness and interpretability.

Abstract

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework -- LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many.