推荐系统综述  

Review of recommendation system

作　　者：于蒙 何文涛 周绪川[1] 崔梦天 吴克奇 周文杰 YU Meng;HE Wentao;ZHOU Xuchuan;CUI Mengtian;WU Keqi;ZHOU Wenjie(The Key Laboratory for Computer Systems of State Ethnic Affairs Commission(Southwest Minzu University),Chengdu Sichuan 610041,China)

机构地区：[1]计算机系统国家民委重点实验室(西南民族大学),成都610041

出　　处：《计算机应用》2022年第6期1898-1913,共16页journal of Computer Applications

基　　金：国家自然科学基金资助项目(12050410248);四川省科技计划项目(2021YFH0120);西南民族大学研究生创新型科研项目(CX2020SZ04)。

摘　　要：随着网络应用的不断发展,网络资源呈指数型增长,信息过载现象日益严重,如何高效获取符合需求的资源成为困扰人们的问题之一。推荐系统能对海量信息进行有效过滤,为用户推荐符合其需求的资源。对推荐系统的研究现状进行详细介绍,包括基于内容的推荐、协同过滤推荐和混合推荐这三种传统推荐方式,并重点分析了基于卷积神经网络(CNN)、深度神经网络(DNN)、循环神经网络(RNN)和图神经网络(GNN)这四种常见的深度学习推荐模型的研究进展;归纳整理了推荐领域常用的数据集,同时分析对比了传统推荐算法和基于深度学习的推荐算法的差异。最后,总结了实际应用中具有代表性的推荐模型,讨论了推荐系统面临的挑战和未来的研究方向。With the continuous development of network applications,network resources are growing exponentially and information overload is becoming increasingly serious,so how to efficiently obtain the resources that meet the user needs has become one of the problems that bothering people.Recommendation system can effectively filter mass information and recommend the resources that meet the users needs.The research status of the recommendation system was introduced in detail,including three traditional recommendation methods of content-based recommendation,collaborative filtering recommendation and hybrid recommendation,and the research progress of four common deep learning recommendation models based on Convolutional Neural Network(CNN),Deep Neural Network(DNN),Recurrent Neural Network(RNN)and Graph Neural Network(GNN)were analyzed in focus.The commonly used datasets in recommendation field were summarized,and the differences between the traditional recommendation algorithms and the deep learning-based recommendation algorithms were analyzed and compared.Finally,the representative recommendation models in practical applications were summarized,and the challenges and the future research directions of recommendation system were discussed.

关 键 词：推荐算法 协同过滤 深度学习 卷积神经网络 深度神经网络 循环神经网络 图神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]