期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 191, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2021.116240
关键词
Graph representation learning; Graph neural network; Recommender system; Attention mechanism
类别
资金
- Zhejiang Provincial Natural Science Foundation of China [LQ20F030016]
- National Natural Science Foundation of China [61802132, 62006215]
This paper introduces a novel deep GNN model MAF-GNN, which improves the quality of latent feature representations for users and items through multi-graph attention fusion and multi-scale latent feature modules. Experimental results show that MAF-GNN outperforms existing methods in recommendation systems.
Graph neural networks (GNNs), with their promising potential to learn effective graph representation, have been widely used for recommender systems, in which the given graph data contains abundant users, items, and their historical interaction information. How to obtain preferable latent representations for both users and items is one of the key issues for GNN-based recommendation. This paper develops a novel deep GNN model with multi-graph attention fusion, MAF-GNN. This framework constructs two feature graph attention modules and a multi-scale latent features module, to generate better user and item latent features from input information. Specifically, the dual-branch residual graph attention (DBRGA) module is presented to extract neighbors' similar features from user and item graphs effectively and easily. Then multi-scale latent matrices are captured by applying non-linear transformations which are embedded to reduce the cost of dimension selection. Furthermore, a hybrid fusion graph attention (HFGA) module is designed to obtain valuable collaborative information from the user-item interaction graph, aiming to further refine the latent embedding of users and items. Finally, the whole MAF-GNN framework is optimized by a geometric factorized regularization loss. Extensive experiment results on both synthetic and real-world datasets illustrate that MAF-GNN can achieve better recommendation performance with a certain level of interpretability than some existing approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据