Universal Multi-modal Entity Alignment via Iteratively Fusing Modality Similarity Paths

TL;DR

This paper introduces PathFusion, a novel multi-modal entity alignment method that effectively fuses heterogeneous modality information through path-based modeling and iterative fusion, significantly outperforming existing approaches.

Contribution

PathFusion offers a unified, efficient approach to multi-modal entity alignment by combining path-based representation with iterative modality fusion, addressing previous modeling and fusion shortcomings.

Findings

Achieves 22.4%-28.9% improvement on Hits@1

Attains 0.194-0.245 increase on MRR

Outperforms state-of-the-art methods on real-world datasets

Abstract

The objective of Entity Alignment (EA) is to identify equivalent entity pairs from multiple Knowledge Graphs (KGs) and create a more comprehensive and unified KG. The majority of EA methods have primarily focused on the structural modality of KGs, lacking exploration of multi-modal information. A few multi-modal EA methods have made good attempts in this field. Still, they have two shortcomings: (1) inconsistent and inefficient modality modeling that designs complex and distinct models for each modality; (2) ineffective modality fusion due to the heterogeneous nature of modalities in EA. To tackle these challenges, we propose PathFusion, consisting of two main components: (1) MSP, a unified modeling approach that simplifies the alignment process by constructing paths connecting entities and modality nodes to represent multiple modalities; (2) IRF, an iterative fusion method that effectively combines information from different modalities using the path as an information carrier. Experimental results on real-world datasets demonstrate the superiority of PathFusion over state-of-the-art methods, with 22.4%-28.9% absolute improvement on Hits@1, and 0.194-0.245 absolute improvement on MRR.