Exploring Link Prediction over Hyper-Relational Temporal Knowledge Graphs Enhanced with Time-Invariant Relational Knowledge

There has been an increasing interest in studying graph reasoning over hyper-relational KGs (HKGs). Compared with traditional knowledge graphs (KGs), HKGs introduce additional factual information in the form of qualifiers (key-value pairs) for each KG fact that helps to better restrict the fact validity. Meanwhile, due to the ever-evolving nature of world knowledge, extensive parallel works have been studying temporal KG (TKG) reasoning. Each TKG fact can be viewed as a KG fact coupled with a timestamp (or time period) specifying its time validity. The existing HKG reasoning approaches do not consider temporal information because it is not explicitly specified in previous benchmark datasets. Besides, traditional TKG reasoning methods only focus on temporal reasoning and have no way to learn from qualifiers. To this end, we aim to fill the gap between TKG and HKG reasoning. We develop two new benchmark hyper-relational TKG (HTKG) datasets, i.e., Wiki-hy and YAGO-hy, and propose an HTKG reasoning model that efficiently models both temporal facts and qualifiers. We further exploit additional time-invariant relational knowledge from the Wikidata knowledge base to improve HTKG reasoning. Time-invariant relational knowledge serves as the knowledge that remains unchanged in time (e.g., Sasha Obama is the child of Barack Obama). Experimental results show that our model achieves strong performance on HTKG link prediction and can be enhanced by jointly leveraging both temporal and time-invariant relational knowledge.