Knowledge Graph Completion Based on Entity Descriptions in Hyperbolic Space

Abstract

Hyperbolic space has received extensive attention because it can accurately and concisely represent hierarchical data. Currently, for knowledge graph completion tasks, the introduction of exogenous information of entities can enrich the knowledge representation of entities, but there is a problem that entities have different levels under different relations, and the embeddings of different entities in Euclidean space often requires high dimensional space to distinguish. Therefore, in order to solve the above problem, we propose a method that use entity descriptions to complete the knowledge graph in the Poincaré ball model of hyperbolic space. In this method, the text representation of entity descriptions is in Euclidean space and mapped to hyperbolic space through exponential map. Next, the triple embeddings are initialized in hyperbolic space, and the structured representation of the triple is trained by the hyperbolic model. Finally, the text representation and the structured representation of the entity are cross-fused in hyperbolic space, and then the balance factors are used to adjust the unbalanced energy function. Experimental results show that, compared with baseline models, the proposed method can improve the performance of knowledge graphs completion.

An Evolutionary Prediction Model for Enterprise Basic Research Based on Knowledge Graph

“…Another set of researchers has primarily used neural networks and other machine-learning methods for graph construction. Zhang and Yu [10] proposed an end-to-end learning model for knowledge graph completion using a weighted graph CNN and relation induction mechanism, which was validated in general databases. However, the transferability of this knowledge graph completion model to tasks such as information retrieval has yet to be explored.…”