DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing

TL;DR

This paper introduces DHGE, a novel dual-view hyper-relational knowledge graph embedding model that improves link prediction and entity typing by capturing hierarchical structures, supported by new datasets and experimental validation.

Contribution

The paper proposes a dual-view hyper-relational KG structure and a corresponding embedding model, DHGE, along with new datasets for link prediction and entity typing tasks.

Findings

DHGE outperforms baseline models on DH-KG datasets

New datasets JW44K-6K and HTDM are constructed and publicly released

Demonstrates practical application in hypertension treatment

Abstract

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.