A unified hierarchical attention framework for sequential recommendation by fusing long and short-term preferences
作者：
Highlights：
• A novel unified framework for sequential recommendation is proposed.
• Multi-head self-attention captures both the general and dynamic user preferences.
• Hierarchical attention obtains the item–item interaction features in higher order.
• A joint learning mechanism fuses the long and short-term features effectively.
• The proposed model achieves significant improvement over other related method.
摘要
•A novel unified framework for sequential recommendation is proposed.•Multi-head self-attention captures both the general and dynamic user preferences.•Hierarchical attention obtains the item–item interaction features in higher order.•A joint learning mechanism fuses the long and short-term features effectively.•The proposed model achieves significant improvement over other related method.
论文关键词：Behavior sequences,Feature interactions,Hierarchical attention,Long and short-term preferences,Sequential recommendation
论文评审过程：Received 2 August 2021, Revised 21 January 2022, Accepted 28 March 2022, Available online 8 April 2022, Version of Record 12 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117102
