A knowledge-enhanced contextual bandit approach for personalized recommendation in dynamic domains

作者：

Highlights：

• We combine a knowledge graph and the bandit method for constructing personalized, dynamic recommendations.

• We propose an intention-selection mechanism for item selection in recommender systems.

• We propose the one choice multi change strategy for a contextual multiarmed bandit.

• Knowledge graphs effectively address the lack of knowledge in recommender systems.

摘要

•We combine a knowledge graph and the bandit method for constructing personalized, dynamic recommendations.•We propose an intention-selection mechanism for item selection in recommender systems.•We propose the one choice multi change strategy for a contextual multiarmed bandit.•Knowledge graphs effectively address the lack of knowledge in recommender systems.

论文关键词：Recommender system,Knowledge graph,Contextual multi-armed bandit,Dynamic domain

论文评审过程：Received 27 October 2021, Revised 25 May 2022, Accepted 26 May 2022, Available online 3 June 2022, Version of Record 17 June 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109158