Towards Time-Aware Knowledge Hypergraph Link Prediction

A knowledge hypergraph is a form of the heterogeneous graph representing the real world through n-ary relations, but the existing knowledge hypergraphs are usually incomplete in both general and vertical domains. Therefore, it is a challenging task to reason the missing links through the existing links in the knowledge hypergraph. Most of the current studies use n-ary relation-based knowledge representation learning methods to accomplish the task of link prediction in knowledge hypergraphs, but they only learn the embedding vectors of entities and relations from time-unknown hyperedges without considering the influence of temporal factors on the dynamic evolution of facts, which leads to poor prediction performance in dynamic environments. Firstly, based on the definition of temporal knowledge hypergraph that proposed by this paper for the first time, we propose a link prediction model for temporal knowledge hypergraphs, and learn static and dynamic representations of entities from their roles, positions, and timestamps of temporal hyperedges, which are merged in a certain proportion and utilized as final entity embedding vectors for link prediction tasks to realize the full exploitation of hyperedge temporal information. At the same time, it is theoretically proved that the proposed model is fully expressive and has linear space complexity. In addition, a temporal knowledge hypergraph dataset CB67 is constructed from the public business data of listed companies, and a large number of experimental evaluations are conducted on this dataset. The experimental results show that the proposed model can effectively perform the link prediction task on the temporal knowledge hypergraph dataset. © 2023 Chinese Academy of Sciences. All rights reserved.