HyperFM: Fact-Centric Multimodal Fusion for Link Prediction over Hyper-Relational Knowledge Graphs

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. Neverthe-less, traditional multimodal 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 be-tween different data modalities while accommodating the hyper-relational structure of the KG in a fact-centric manner via a customized Hypergraph Transformer. We evaluate Hy-perFM against a sizeable collection of base-lines in link prediction tasks on two real-world KG datasets. The 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.