Knowledge Graph Completion Model Based on Entity Importance Integration
YANG Shuai
HAN Bin
Abstract：Knowledge graph is a research hotspot in the field of artificial intelligence.Due to the lack and incompleteness of knowledge graph data,knowledge completion uses given entities and relationships to complete the missing part.The existing TransE model and RotatE model both complete the task of knowledge completion well,but they both ignore the important information of enti-ties.In this paper,an improved model is proposed,which adds entity importance information into the RotatE model.The PageRank algorithm is used to calculate the entity importance.At the same time,the importance information is deeply excavated,and the enti-ty influence factors are defined by combining entity degree information and agglomeration coefficient information.Different weights are assigned to different entities in the learning process to improve the completion performance of the model.Experimental results show that compared with the original model and other baseline models,the improved model has improved the completion effect on different data sets.
Keywords：knowledge graphentity importanceRotatE modellink prediction
Publication Date：2025-05-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 1333-1337,1344 )