Progressively Modality Freezing for Multi-Modal Entity Alignment
This work improves entity alignment for knowledge graph integration, though it appears incremental as it builds on existing fusion paradigms.
The paper tackles the problem of multi-modal entity alignment across heterogeneous knowledge graphs by addressing irrelevant features and modal inconsistencies, achieving state-of-the-art performance across nine datasets.
Multi-Modal Entity Alignment aims to discover identical entities across heterogeneous knowledge graphs. While recent studies have delved into fusion paradigms to represent entities holistically, the elimination of features irrelevant to alignment and modal inconsistencies is overlooked, which are caused by inherent differences in multi-modal features. To address these challenges, we propose a novel strategy of progressive modality freezing, called PMF, that focuses on alignmentrelevant features and enhances multi-modal feature fusion. Notably, our approach introduces a pioneering cross-modal association loss to foster modal consistency. Empirical evaluations across nine datasets confirm PMF's superiority, demonstrating stateof-the-art performance and the rationale for freezing modalities. Our code is available at https://github.com/ninibymilk/PMF-MMEA.