A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment

TL;DR

This paper presents FGWEA, an unsupervised framework for entity alignment across knowledge graphs that leverages Fused Gromov-Wasserstein distance and a progressive optimization algorithm to outperform existing methods without supervision.

Contribution

Introducing FGWEA, a novel unsupervised entity alignment method using FGW distance and a three-stage optimization process for improved structural and semantic matching.

Findings

FGWEA surpasses 21 baselines on multiple datasets.

It operates effectively without supervision or hyper-parameter tuning.

The method handles multiple languages and diverse KGs.

Abstract

Entity alignment is the task of identifying corresponding entities across different knowledge graphs (KGs). Although recent embedding-based entity alignment methods have shown significant advancements, they still struggle to fully utilize KG structural information. In this paper, we introduce FGWEA, an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein (FGW) distance, allowing for a comprehensive comparison of entity semantics and KG structures within a joint optimization framework. To address the computational challenges associated with optimizing FGW, we devise a three-stage progressive optimization algorithm. It starts with a basic semantic embedding matching, proceeds to approximate cross-KG structural and relational similarity matching based on iterative updates of high-confidence entity links, and ultimately culminates in a global structural comparison between KGs. We perform extensive experiments on four entity alignment datasets covering 14 distinct KGs across five languages. Without any supervision or hyper-parameter tuning, FGWEA surpasses 21 competitive baselines, including cutting-edge supervised entity alignment methods. Our code is available at https://github.com/squareRoot3/FusedGW-Entity-Alignment.