RHKH: Relational Hypergraph Neural Network for Link Prediction on N-ary Knowledge Hypergraph

Yuzhuo Wang, Junwei He, Hongzhi Wang

Abstract: All along, KG completion relied on link prediction has always been the focus of researchers. However, overwhelming majority of them can only serve 2-ary KGs. While in practice, knowledge hypergraphs (KH) covering facts beyond binary relations are far more ubiquitous but receive little attention. When confronted with them, massive studies for KGs show inadaptability. The several work towards N-ary KHs generally simply extend KG methods. And they usually transform N-ary knowledge into role-value pairs or triples, largely simplifying inherent association within each piece of knowledge. Furthermore, previous models study each N-ary knowledge independently, resulting in structural correlations among them being completely neglected. Motivated by these, avoiding breaking knowledge structure in KHs like previous studies do, based on original knowledge formats, we propose the first KH reasoning model based on an innovative relational hypergraph neural network (RHNN), RHKH. Challenged by complicated compositions indicated by the original format of N-ary tuples, association within and among each knowledge is discovered through RHNN. It considers complex interactions between relation and entities involved in the same knowledge as well. To refine such interactions, semantic components at each arity-position of relations are distinguished, along with introducing position-specific shift. Extensive experiments demonstrate the effectiveness of our RHKH.

Primary Subject Area: [Content] Multimodal Fusion

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: The proposed RHKH model, based on a Relational Hypergraph Neural Network (RHNN), is highly relevant to the conference's focus on Multimodal Fusion and Multimedia Applications. Addressing the gap in traditional Knowledge Graph (KG) completion, RHKH better represents complex, N-ary relationships found in real-world data, enhancing multimodal fusion and multimedia applications such as recommendation systems and semantic web technologies. By preserving the original knowledge structure in Knowledge Hypergraphs (KHs) and refining interactions between relations and entities, RHKH advances multimodal fusion techniques and improves the performance of multimedia applications.

Submission Number: 5743