Affiliations: Army Engineering University of PLA, Nanjing, Jiangsu, China
Correspondence:
[*]
Corresponding authors: Hong-Jun Zhang and Zi-Xuan Zhang, Army Engineering University of PLA, Nanjing, Jiangsu, China. E-mail: [email protected] and E-mail: [email protected].
Abstract: Knowledge graph embedding is aimed at capturing the semantic information of entities by modeling the structural information between entities. For long-tail entities which lack sufficient structural information, general knowledge graph embedding models often show relatively low performance in link prediction. In order to solve such problems, this paper proposes a general knowledge graph embedding framework to learn the structural information as well as the attribute information of the entities simultaneously. Under this framework, a H-AKRL (Hypergraph Neural Networks based Attribute-embodied Knowledge Representation Learning) model is put forward, where the hypergraph neural network is used to model the correlation between entities and attributes at a higher level. The complementary relationship between attribute information and structural information is taken full advantage of, enabling H-AKRL to finally achieve the goal of improving link prediction performance. Experiments on multiple real-world data sets show that the H-AKRL model has significantly improved the link prediction performance, especially in the embeddings of long tail entities.
