@inproceedings{lu-etal-2025-hyperfm,
    title = "{H}yper{FM}: Fact-Centric Multimodal Fusion for Link Prediction over Hyper-Relational Knowledge Graphs",
    author = "Lu, Yuhuan  and
      Yu, Weijian  and
      Jing, Xin  and
      Yang, Dingqi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.acl-long.142/",
    doi = "10.18653/v1/2025.acl-long.142",
    pages = "2818--2830",
    ISBN = "979-8-89176-251-0",
    abstract = "With the ubiquity of hyper-relational facts in modern Knowledge Graphs (KGs), existing link prediction techniques mostly focus on learning the sophisticated relationships among multiple entities and relations contained in a fact, while ignoring the multimodal information, which often provides additional clues to boost link prediction performance. Nevertheless, traditional multimodel fusion approaches, which are mainly designed for triple facts under either entity-centric or relation-guided fusion schemes, fail to integrate the multimodal information with the rich context of the hyper-relational fact consisting of multiple entities and relations. Against this background, we propose **HyperFM**, a **Hyper**-relational **F**act-centric **M**ultimodal Fusion technique. It effectively captures the intricate interactions between different data modalities while accommodating the hyper-relational structure of the KG in a fact-centric manner via a customized Hypergraph Transformer. We evaluate HyperFM against a sizeable collection of baselines in link prediction tasks on two real-world KG datasets. Results show that HyperFM consistently achieves the best performance, yielding an average improvement of 6.0-6.8{\%} over the best-performing baselines on the two datasets. Moreover, a series of ablation studies systematically validate our fact-centric fusion scheme."
}