PSQE: A Theoretical-Practical Approach to Pseudo Seed Quality Enhancement for Unsupervised MMEA

2026-02-26

AI Summary

This work addresses the limitations imposed by low-quality pseudo-seeds and imbalanced graph coverage in unsupervised multimodal entity alignment, which severely degrade model performance in sparse regions. To mitigate these issues, we propose a plug-and-play Pseudo-Seed Quality Enhancement (PSQE) framework that integrates multimodal information and incorporates a clustering-based resampling strategy to simultaneously improve pseudo-seed accuracy and balance structural coverage across the graph. Our theoretical analysis provides the first insight into the dual role of pseudo-seeds in contrastive learning—simultaneously influencing both attraction and repulsion terms. Experimental results demonstrate that PSQE significantly outperforms existing baselines, achieving notable improvements in alignment performance within sparse regions and thereby validating both the efficacy of the proposed method and the underlying theoretical insights.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Multimodal Entity Alignment
• Unsupervised Learning
• Pseudo Seeds
• Graph Coverage Imbalance
• Knowledge Graph

Innovation

• Pseudo-Seed Quality Enhancement
• Multimodal Entity Alignment
• Unsupervised Learning
• Contrastive Learning
• Clustering-Resampling