计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (3): 205-212.DOI: 10.3778/j.issn.1002-8331.2209-0027

• 模式识别与人工智能 • 上一篇    下一篇

基于残差网络的轻量级图卷积推荐方法

唐宇,吴贞东   

  1. 四川师范大学 计算机科学学院,成都 610101
  • 出版日期:2024-02-01 发布日期:2024-02-01

Light Graph Convolution Recommendation Method Based on Residual Network

TANG Yu, WU Zhendong   

  1. College of Computer, Sichuan Normal University, Chengdu 610101, China
  • Online:2024-02-01 Published:2024-02-01

摘要: 针对现有基于图卷积网络的推荐模型存在消息传播链路不完善、最终节点表示冗余的问题,提出了一种基于残差网络的轻量级图卷积推荐方法(ResLightGCN)。引入残差结构建立同一节点相邻层之间的消息传播网络,扩充了信息传播路径;从语义角度上优化最终节点的表示,即不考虑没有消息传播的图卷积层;在四个公开数据集上对ResLightGCN进行评价,实验结果表明 提出的模型优于现有的几种基线模型,特别是在Yelp和Amazon_Books数据集上,ResLightGCN模型的NDCG@10评价指标比最佳基线模型分别提升了16.2%和15.8%。

关键词: 推荐系统, 图神经网络, 协同过滤, 残差网络, 消息传播

Abstract: In order to solve the problem of imperfect message propagation links and redundant representation of final nodes in the existing recommendation model based on graph convolution network, this paper proposes a light graph convolution network recommendation model based on residual network (ResLightGCN). Firstly, the residual structure is employed to establish the message propagation network between adjacent layers of the same node, which expands the information propagation path. Secondly, the final node representation is optimized from the semantic point of view, that is, the graph convolution layer without message propagation is not considered. Finally, ResLightGCN is evaluated on four public data sets. Experimental results demonstrate that the proposed model outperforms multiple existing baseline models. Especially, the performance of ResLightGCN is improved by 16.2% and 15.8% respectively compared with the best baseline model in terms of evaluation metrics NDCG@10 on Yelp and Amazon_Books datasets.

Key words: recommendation system, graph neural network, collaborative filtering, residual network, message propagation