A path-based relation networks model for knowledge graph completion

作者：

Highlights：

• To solve the incompleteness of the knowledge graph, the completion of the knowledge graph is required.

• The various paths of the knowledge graph are valuable information that can infer missing knowledge.

• It is possible to generate training data that can learning a model based on extracted paths.

• The relation network enables relational learning between paths and shows competitive performance.

摘要

•To solve the incompleteness of the knowledge graph, the completion of the knowledge graph is required.•The various paths of the knowledge graph are valuable information that can infer missing knowledge.•It is possible to generate training data that can learning a model based on extracted paths.•The relation network enables relational learning between paths and shows competitive performance.

论文关键词：Knowledge graph completion,Relation network,Link prediction,Triple classification

论文评审过程：Received 29 October 2020, Revised 21 April 2021, Accepted 22 May 2021, Available online 27 May 2021, Version of Record 12 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115273