@inproceedings{huang-etal-2024-progressively,
    title = "Progressively Modality Freezing for Multi-Modal Entity Alignment",
    author = "Huang, Yani  and
      Zhang, Xuefeng  and
      Zhang, Richong  and
      Chen, Junfan  and
      Kim, Jaein",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.acl-long.190/",
    doi = "10.18653/v1/2024.acl-long.190",
    pages = "3477--3489",
    abstract = "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. Our code is available at https://github.com/ninibymilk/PMF-MMEA."
}