Knowledge graph embedding by translating in time domain space for link prediction

作者：

Highlights：

• Propose a novel knowledge graph embedding model called TimE.

• Propose a cross-operation to model inverse and symmetric relations.

• TimE only requires triples in knowledge graphs, and no other data or processes.

摘要

•Propose a novel knowledge graph embedding model called TimE.•Propose a cross-operation to model inverse and symmetric relations.•TimE only requires triples in knowledge graphs, and no other data or processes.

论文关键词：Knowledge graph embedding,Link prediction,Cross-operation,Self-interaction

论文评审过程：Received 27 May 2020, Revised 21 October 2020, Accepted 23 October 2020, Available online 5 November 2020, Version of Record 24 December 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106564