Entity knowledge transfer-oriented dual-target cross-domain recommendations

作者：

Highlights：

• A new entity embedding based on entity interaction and side information is proposed.

• A dual attention mechanism is proposed to realize dual-domain recommendations.

• A deep belief network model with multiple regularization parameters is devised.

• The extensive experiments show that our approach is superior to existing models.

摘要

•A new entity embedding based on entity interaction and side information is proposed.•A dual attention mechanism is proposed to realize dual-domain recommendations.•A deep belief network model with multiple regularization parameters is devised.•The extensive experiments show that our approach is superior to existing models.

论文关键词：Transfer learning,Dual-attention mechanism,Deep belief network,Cross-domain recommendations

论文评审过程：Received 25 November 2021, Revised 5 January 2022, Accepted 19 January 2022, Available online 31 January 2022, Version of Record 3 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116591