Deep multi-graph neural networks with attention fusion for recommendation

作者：

Highlights：

• A novel deep GNN model with multi-graph attention fusion mechanism is proposed.

• A dual-branch residual graph attention module is developed.

• A hybrid fusion graph attention module is designed to obtain valuable information.

• Multi-scale latent matrices are designed to reduce significantly the time cost.

摘要

•A novel deep GNN model with multi-graph attention fusion mechanism is proposed.•A dual-branch residual graph attention module is developed.•A hybrid fusion graph attention module is designed to obtain valuable information.•Multi-scale latent matrices are designed to reduce significantly the time cost.

论文关键词：Graph representation learning,Graph neural network,Recommender system,Attention mechanism

论文评审过程：Received 1 April 2021, Revised 30 July 2021, Accepted 13 November 2021, Available online 3 December 2021, Version of Record 8 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116240