DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing
This work addresses the problem of representing hierarchical structures in hyper-relational knowledge graphs for researchers in knowledge representation, offering incremental improvements over single-view methods.
The paper tackles the limitation of existing hyper-relational knowledge graph embedding methods by proposing a dual-view structure (DH-KG) that includes instance and ontology views, and introduces DHGE, a model that outperforms baselines on link prediction and entity typing tasks using new datasets like JW44K-6K and HTDM.
In the field of representation learning on knowledge graphs (KGs), a hyper-relational fact consists of a main triple and several auxiliary attribute-value descriptions, which is considered more comprehensive and specific than a triple-based fact. However, currently available hyper-relational KG embedding methods in a single view are limited in application because they weaken the hierarchical structure that represents the affiliation between entities. To overcome this limitation, we propose a dual-view hyper-relational KG structure (DH-KG) that contains a hyper-relational instance view for entities and a hyper-relational ontology view for concepts that are abstracted hierarchically from the entities. This paper defines link prediction and entity typing tasks on DH-KG for the first time and constructs two DH-KG datasets, JW44K-6K, extracted from Wikidata, and HTDM based on medical data. Furthermore, we propose DHGE, a DH-KG embedding model based on GRAN encoders, HGNNs, and joint learning. DHGE outperforms baseline models on DH-KG, according to experimental results. Finally, we provide an example of how this technology can be used to treat hypertension. Our model and new datasets are publicly available.