Group event recommendation based on graph multi-head attention network combining explicit and implicit information

作者：

Highlights：

• We establish a general group event recommendation framework in EBSN.

• We alleviate the problem of sparse data in group recommendation and solve the problem of learning vector redundancy.

• We produce better user and event vector representations by using the multi-head attention mechanism.

• Experimental results on two real-world datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods on group event recommendation.

摘要

•We establish a general group event recommendation framework in EBSN.•We alleviate the problem of sparse data in group recommendation and solve the problem of learning vector redundancy.•We produce better user and event vector representations by using the multi-head attention mechanism.•Experimental results on two real-world datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods on group event recommendation.

论文关键词：Explicit information,Implicit information,Group recommendation,Graph attention network

论文评审过程：Received 25 May 2021, Revised 12 September 2021, Accepted 20 October 2021, Available online 11 November 2021, Version of Record 11 November 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102797