Learning attention embeddings based on memory networks for neural collaborative recommendation
作者：
Highlights：
• We design a neural network to learn co-attention from user–item interactions.
• The co-attention provides a better solution to memorize long-term dependencies.
• We design a neural collaborative algorithm for incorporating co-attention.
• Our algorithm is augmented with an external memory and neural attention.
• Our algorithm can capture short-term and long-term dependence well.
摘要
•We design a neural network to learn co-attention from user–item interactions.•The co-attention provides a better solution to memorize long-term dependencies.•We design a neural collaborative algorithm for incorporating co-attention.•Our algorithm is augmented with an external memory and neural attention.•Our algorithm can capture short-term and long-term dependence well.
论文关键词：Memory networks,Collaborative filtering,Attention embeddings,Behavioral patterns,Recommender systems
论文评审过程：Received 27 July 2020, Revised 12 June 2021, Accepted 12 June 2021, Available online 17 June 2021, Version of Record 19 June 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115439
