Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (10): 41-49.DOI: 10.3778/j.issn.1002-8331.2110-0345

• Research Hotspots and Reviews • Previous Articles     Next Articles

Research on Graph Neural Network Recommendation Method

LIU Xin, MEI Hongyan, WANG Jiahao, LI Xiaohui   

  1. College of Electronic and Information Engineering, Liaoning University of Technology, Jinzhou, Liaoning 121001, China
  • Online:2022-05-15 Published:2022-05-15

图神经网络推荐方法研究

刘鑫,梅红岩,王嘉豪,李晓会   

  1. 辽宁工业大学 电子与信息工程学院,辽宁 锦州 121001

Abstract: Graph neural network has a good application effect in many application fields because of its characteristics, the combination of graph neural network and recommendation has become one of the research hot spots. Using graph neural network in recommendation can significantly improve the level of recommendation in complex environment. In this paper, the graph neural network method, personalized recommendation and group recommendation are introduced respectively. The recommendation methods based on graph neural network are summarized, focusing on graph neural network and its recent research achievements in the field of recommendation. The recommendation research status and the difficulties in further development are analyzed. According to the advantages of graph neural network, the feasibility of combining graph neural network with group recommendation is analyzed and prospected.

Key words: graph neural network, group recommendation, deep learning, recommendation system

摘要: 图神经网络因其特性在许多应用领域展露锋芒,将图神经网络与推荐相结合成为研究热点之一。在推荐中使用图神经网络方法,能够在复杂环境中显著提高推荐的水平。对图神经网络的方法、个性化推荐和群组推荐分别进行总结介绍;对基于图神经网络的推荐方法进行概述,重点对图神经网络及其近年来在推荐领域的研究成果进行归纳总结;分析了推荐研究现状和阻碍其进一步发展的困难,并根据图神经网络的优势对图神经网络与群组推荐结合进行了可行性分析及展望。

关键词: 图神经网络, 群组推荐, 深度学习, 推荐系统