Heterogeneous type-specific entity representation learning for recommendations in e-commerce network

作者：

Highlights：

• A novel heterogeneous type-specific entity representation method is proposed.

• A hybrid translation-based relation embedding is designed for rating prediction.

• An explainable strategy based on entity characteristics is proposed.

摘要

•A novel heterogeneous type-specific entity representation method is proposed.•A hybrid translation-based relation embedding is designed for rating prediction.•An explainable strategy based on entity characteristics is proposed.

论文关键词：Heterogeneous information,Attention mechanism,Representation learning,Recommendation

论文评审过程：Received 15 January 2021, Revised 28 March 2021, Accepted 4 May 2021, Available online 10 May 2021, Version of Record 10 May 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102629