当前位置: X-MOL 学术IEEE Trans. Ind. Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Separated Graph Neural Networks for Recommendation Systems
IEEE Transactions on Industrial Informatics ( IF 12.3 ) Pub Date : 2022-08-01 , DOI: 10.1109/tii.2022.3194659
Jianwen Sun 1 , Lu Gao 1 , Xiaoxuan Shen 1 , Sannyuya Liu 1 , Ruxia Liang 1 , Shangheng Du 1 , Shengyingjie Liu 1
Affiliation  

Automatic recommendation has become an increasingly relevant problem for industries, which allows users to discover items that match their tastes and enables the system to target items at the right users. Graph neural networks have attracted many researchers' attention and have become a useful tool for recommendation. However, these models face two major challenges, which are heterogeneous information aggregation and aggregation weight estimation. In this article, we propose a graph neural networks-based recommendation model, i.e., a separated graph neural recommendation (SGNR) model, which achieves high-quality performance. SGNR separates BINs in recommendation systems into two weighted homogeneous networks for users and items, respectively, resolving the heterogeneous information aggregation problem. In addition, a propagation coefficient estimation method is proposed, which combines parametric and nonparametric estimation strategies. And, it is constructed with three characteristics, which are collaborative, side-information constrained, and adaptive. Thereinto, a three-hierarchy attention operator is contained for feature fusion, which optimizes the feature aggregation process via a more sensible and flexible propagation mechanism. Experimental results on four public databases indicate that the proposed methods perform better than the state-of-the-art recommendation algorithms on prediction accuracy in terms of quantitative assessments and achieve readability and interpretability to some extent.

中文翻译:

推荐系统的分离图神经网络

自动推荐已成为与行业越来越相关的问题,它允许用户发现符合他们口味的商品,并使系统能够将商品定位到正确的用户。图神经网络引起了许多研究人员的关注,并已成为一种有用的推荐工具。然而,这些模型面临两大挑战,即异构信息聚合和聚合权重估计。在本文中,我们提出了一种基于图神经网络的推荐模型,即分离图神经网络推荐(SGNR)模型,该模型实现了高质量的性能。SGNR 将推荐系统中的 BIN 分为用户和项目的两个加权同构网络,解决异构信息聚合问题。此外,提出了一种将参数估计策略与非参数估计策略相结合的传播系数估计方法。并且,它具有三个特征,即协作、边信息约束和自适应。其中,包含用于特征融合的三层注意力算子,通过更明智和灵活的传播机制优化特征聚合过程。在四个公共数据库上的实验结果表明,所提出的方法在定量评估方面的预测准确性优于最先进的推荐算法,并在一定程度上实现了可读性和可解释性。它们是协作的、辅助信息受限的和自适应的。其中,包含用于特征融合的三层注意力算子,通过更明智和灵活的传播机制优化特征聚合过程。在四个公共数据库上的实验结果表明,所提出的方法在定量评估方面的预测准确性优于最先进的推荐算法,并在一定程度上实现了可读性和可解释性。它们是协作的、辅助信息受限的和自适应的。其中,包含用于特征融合的三层注意力算子,通过更明智和灵活的传播机制优化特征聚合过程。在四个公共数据库上的实验结果表明,所提出的方法在定量评估方面的预测准确性优于最先进的推荐算法,并在一定程度上实现了可读性和可解释性。
更新日期:2022-08-01
down
wechat
bug