期刊
JOURNAL OF SUPERCOMPUTING
卷 79, 期 8, 页码 8295-8321出版社
SPRINGER
DOI: 10.1007/s11227-022-04985-4
关键词
Recommender system; Social network; Graph attention network
This paper proposes a multi-relational attention network called MRAN for social recommendation, which addresses the issues of data sparsity and over-smoothing. By incorporating user social relations and item homogeneous relations, simulating influence diffusion structure, and using a two-level attention mechanism, the proposed model outperforms previous methods according to experiments.
Graph Neural Networks have been widely used in social recommendation systems. However, with the increase of graph nodes and diffusion depth, they tend to suffer from graph sparsity and over-smoothing, which inhibit their performance. In this work, we propose the multi-relational attention network, named as MRAN, for social recommendation. Our model has three distinctive characteristics: (i) it alleviates the data sparsity problem in social recommendation scenarios by incorporating both user social relations and item homogeneous relations as supplementary information; (ii) it mimics the structure of influence diffusion in user and item domain via an iteratively aggregating structure; (iii) it has a two-level attention mechanism at the diffusion and aggregating level, enabling it to differentiate importance of embeddings to overcome the over-smoothing problem. Experiments conducted on two large-scale representative datasets demonstrate that the proposed model outperforms previous methods substantially. The ablation study shows that the performance of MRAN can be further improved avoid over-smoothing by increasing the diffusion depth.
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