Context-aware item attraction model for session-based recommendation
作者：
Highlights：
• Propose an item attraction model for session-based recommendation.
• Convert sequence-structured sessions into local and global undirected graphs.
• Mine item adjacency relevance in session graphs for users’ general interests.
• Mine item transition relevance in session sequences for users’ temporal interests.
• Design a weighted graph convolutional network for neighbors’ context information.
摘要
•Propose an item attraction model for session-based recommendation.•Convert sequence-structured sessions into local and global undirected graphs.•Mine item adjacency relevance in session graphs for users’ general interests.•Mine item transition relevance in session sequences for users’ temporal interests.•Design a weighted graph convolutional network for neighbors’ context information.
论文关键词：Session-based recommendation,Item attraction,Item relevance,Undirected graph,Context-aware
论文评审过程：Received 10 January 2020, Revised 1 February 2021, Accepted 1 March 2021, Available online 13 March 2021, Version of Record 26 March 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114834
