基于自监督的预训练在推荐系统中的研究  

Research on self-supervised pre-training for recommender systems

作　　者：杨纪元 马沐阳 任鹏杰[1] 陈竹敏[1] 任昭春[1] 辛鑫 蔡飞[2] 马军[1] YANG Jiyuan;MA Muyang;REN Pengjie;CHEN Zhumin;REN Zhaochun;XIN Xin;CAI Fei;MA Jun(School of Computer Science and Technology,Shandong University,Qingdao 266237,Shandong,China;School of Systems Engineering,National University of Defense Technology,Changsha 410015,Hunan,China)

机构地区：[1]山东大学计算机科学与技术学院,山东青岛266237 [2]国防科技大学系统工程学院,湖南长沙410015

出　　处：《山东大学学报（理学版）》2024年第7期1-26,共26页Journal of Shandong University(Natural Science)

基　　金：国家自然科学基金资助项目(61902219,61972234,62072279,62102234,62202271,62272274);山东省自然科学基金资助项目(ZR2021QF129,ZR2022QF004);国家重点研发项目(2020YFB1406704,2022YFC3303004);山东省科技创新重点项目(2019JZZY010129);腾讯犀牛鸟专项研究计划资助项目(JR-WXG2021411)。

摘　　要：近来涌现一批研究工作探讨如何将预训练技术应用在推荐场景下并构造预训练任务,以此提升最终的推荐性能。对现有的基于预训练的推荐模型研究进展进行重点综述;并对不同的预训练方法进行分类和比较,在3个推荐系统基准数据集上对一些代表性模型进行实验和分析,相关的数据集和代码已开源;最后对预训练的推荐模型的未来发展趋势进行总结和展望。Plenty of recent studies explores the application of pre-training techniques within the context of recommendation scenarios and the design of pre-training tasks in order to enhance the overall performance of recommendation.This paper extensively reviews the progress in research of recommendation models based on pre-training,classifies and compares different pre-training methods,and conducts extensive experiments and analyses on some representative models using three benchmark datasets for recommendation systems.The datasets and codes have been made open source.Finally,we summarize and prospect the future development trend of recommendation models based on pre-training.

关 键 词：推荐系统 综述 预训练模型 自监督学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]