MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid

TL;DR

MEAformer is a transformer-based model for multi-modal entity alignment that dynamically fuses modalities at the entity level, improving robustness and achieving state-of-the-art results across various scenarios.

Contribution

Introduces MEAformer, a novel transformer approach that predicts mutual modality correlations for fine-grained, entity-level fusion in multi-modal entity alignment tasks.

Findings

Achieves state-of-the-art performance in multiple scenarios.

Demonstrates efficiency with limited parameters and runtime.

Provides interpretability in modality fusion.

Abstract

Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images. However, current MMEA algorithms rely on KG-level modality fusion strategies for multi-modal entity representation, which ignores the variations of modality preferences of different entities, thus compromising robustness against noise in modalities such as blurry images and relations. This paper introduces MEAformer, a multi-modal entity alignment transformer approach for meta modality hybrid, which dynamically predicts the mutual correlation coefficients among modalities for more fine-grained entity-level modality fusion and alignment. Experimental results demonstrate that our model not only achieves SOTA performance in multiple training scenarios, including supervised, unsupervised, iterative, and low-resource settings, but also has a limited number of parameters, efficient runtime, and interpretability. Our code is available at https://github.com/zjukg/MEAformer.