PSQE: A Theoretical-Practical Approach to Pseudo Seed Quality Enhancement for Unsupervised Multimodal Entity Alignment

TL;DR

This paper introduces PSQE, a method to enhance pseudo seed quality in unsupervised multimodal entity alignment, improving model performance by balancing seed coverage and leveraging multimodal data.

Contribution

The paper presents PSQE, a novel approach combining multimodal information and clustering-resampling to improve pseudo seed quality in unsupervised entity alignment.

Findings

PSQE improves pseudo seed precision and coverage balance.

Theoretical analysis shows pseudo seeds affect contrastive learning components.

Experimental results demonstrate significant performance gains with PSQE.

Abstract

Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different data modalities, enabling structural data integration that in turn improves the performance of various large language model applications. To lift the requirement of labeled seed pairs that are difficult to obtain, recent methods shifted to an unsupervised paradigm using pseudo-alignment seeds. However, unsupervised entity alignment in multimodal settings remains underexplored, mainly because the incorporation of multimodal information often results in imbalanced coverage of pseudo-seeds within the knowledge graph. To overcome this, we propose PSQE (Pseudo-Seed Quality Enhancement) to improve the precision and graph coverage balance of pseudo seeds via multimodal information and clustering-resampling. Theoretical analysis reveals the impact of pseudo seeds on existing contrastive learning-based MMEA models. In particular, pseudo seeds can influence the attraction and the repulsion terms in contrastive learning at once, whereas imbalanced graph coverage causes models to prioritize high-density regions, thereby weakening their learning capability for entities in sparse regions. Experimental results validate our theoretical findings and show that PSQE as a plug-and-play module can improve the performance of baselines by considerable margins.