Enhanced graph neural network for session-based recommendation

作者：

Highlights：

• Multiple interaction patterns are explicitly modelled in one session graph.

• A new fusion algorithm is proposed to reconstruct the current session graph.

• A new enhanced graph neural network E-GNN model is proposed.

摘要

•Multiple interaction patterns are explicitly modelled in one session graph.•A new fusion algorithm is proposed to reconstruct the current session graph.•A new enhanced graph neural network E-GNN model is proposed.

论文关键词：Session-based recommendation,Interaction pattern,Enhanced graph neural network (E-GNN),Weighted global item graph (WGIG)

论文评审过程：Received 2 April 2022, Revised 17 September 2022, Accepted 19 September 2022, Available online 22 September 2022, Version of Record 1 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118887