太原理工大学学报2025，Vol.56Issue(3)：485-494,10.DOI:10.16355/j.tyut.1007-9432.20230281
基于对比学习的简化图卷积网络推荐算法
Contrastive Learning-based Simplified Graph Convolutional Network Recommendation
于雨晨 1吴斯琦 1赵清华 1吴旭红 1王雷1
作者信息
- 1. 太原理工大学,信息与计算机学院,山西 晋中||太原理工大学,图像与智能实验室,山西 晋中
- 折叠
摘要
Abstract
[Purposes]Considering the problems of the existing Graph Convolutional Network(GCN)recommendation models,such as low model convergence efficiency,over-smoothing,and de-teriorative recommendations for long-tail items caused by the effect of high-degree nodes on presenta-tion learning,a Contrastive Learning-based Simplified Graph Convolutional Network recommenda-tion algorithm(SGCN-CL)is presented.[Methods]The self-supervised learning method was used to generate multiple views for the user and item nodes for contrastive learning,in order to improve the accuracy of model recommendation and effectively improve the recommendation of long-tail items.For each view,the same feature extraction task for different inputs was carried out,and an improved message propagation model SGCN was proposed to carry out feature extraction and enhance model ef-ficiency.The algorithm was evaluated on Amazon-Book,Yelp2018,and Gowalla datasets.[Results]The results show that the recall rates of the above three datasets are increased by 15.4%,4.3%,1.4%,and NDCG increased by 17.8%,4.1%,1.6%,respectively.Additionally,the efficiency of model has increased more than 55%.After the introduction of Contrastive Learning method,the rec-ommendation effect of non-popular long-tail items is also improved.关键词
图卷积网络/自监督学习/对比学习/长尾项目Key words
graph convolutional network/self-supervised learning/contrastive learning/long-tail item分类
信息技术与安全科学引用本文复制引用
于雨晨,吴斯琦,赵清华,吴旭红,王雷..基于对比学习的简化图卷积网络推荐算法[J].太原理工大学学报,2025,56(3):485-494,10.
