A self-supervised graph convolutional model for recommendation with exponential moving average

作     者：Chen, Rui Pang, Kangning Wang, Zonglin Liu, Qingfang Tang, Cundong Chang, Yanshuo Huang, Min 

作者机构：College of Software Engineering Zhengzhou University of Light Industry Zhengzhou450001 China Henan Joint International Research Laboratory of Computer Animation Implementation Technologies Zhengzhou450001 China Information Center Shijiazhuang Posts and Telecommunications Technical College Shijiazhuang050021 China School of Information Science and Technology Northwest University Xi’an710127 United States Insititute for Silk Road Research Xi’an University of Finance and Economics Xi’an710100 China 

出 版 物：《Neural Computing and Applications》 (Neural Comput. Appl.)

年 卷 期：2025年第37卷第9期

页      面：6777-6793页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported in part by the National Natural Science Foundation of China under Grants 62072416  61902361  61975187  and 61802352  in part by Key Research and Development Program of Shaanxi (Program No. 2024GX-YBXM-545)  in part by the Henan Key Research Project of Higher Education Institutions under Grant 22B520046  in part by Key Research and Development Special Project of Henan Province under Grants 221111210500  232102211053  222102210170  222102110045  232102321069  HNKP2024214  and 2023SJGLX369Y  in part by the Natural Science Foundation Project of Henan Province under Grant 222300420582  in part by the Mass Innovation Space Incubation Project under Grant 2023ZCKJ216  in part by the Data Science and Knowledge Engineering Team of Zhengzhou University of Light Industry  and in part by the innovation team of data science and knowledge engineering of Zhengzhou University of Light Industry under Grant 13606000032 

主　　题：Recommender systems 

摘      要：Recommendation algorithms based on graph convolutional networks can integrate user and item node information along with their interaction topology, better capturing the intricate relationships between users and items, thereby enhancing the accuracy of recommender systems. However, existing methods often overlook the impact of noise in user behavior data on recommendation performance. Additionally, when there are too many convolutional layers in the graph, the node representations tend to smoothing, resulting in an inability to accurately distinguish user preferences. To address these issues, we propose a self-supervised graph convolutional model for recommendation with exponential moving average (SGCERec). Specifically, we first employ exponential moving average (EMA) techniques from the field of time-series analysis to denoise the raw user interaction data. Then, by applying layer filtering technique to update the propagation of information and the representation of nodes within the graph convolutional network, we effectively deepen the model hierarchy, enabling the model to gain a deeper understanding of the features and structures of the graph data, thereby improving the performance and effectiveness of the recommender systems. Finally, experimental results on three real datasets show that SGCERec outperforms state-of-the-art recommendation methods across various common evaluation metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.