陈俊帆
点赞：
陈俊帆
点赞：
论文
Progressively Modality Freezing for Multi-Modal Entity Alignment
发布时间：2025-10-22点击次数：
发表刊物：
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), CCF-A
摘要：
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 alignment-relevant 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 state-of-the-art performance and the rationale for freezing modalities.
合写作者：
Yani Huang, Xuefeng Zhang,张日崇,陈俊帆, Jaein Kim
论文类型：
国际学术会议
页面范围：
3477-3489
是否译文：
否
发表时间：
2024-01-01