%A Zeng,Zheni %A Xiao,Chaojun %A Yao,Yuan %A Xie,Ruobing %A Liu,Zhiyuan %A Lin,Fen %A Lin,Leyu %A Sun,Maosong %D 2021 %J Frontiers in Big Data %C %F %G English %K Recommender system,Pre-Trained Model,knowledge transfer,cross-domain transfer,Cold start %Q %R 10.3389/fdata.2021.602071 %W %L %M %P %7 %8 2021-March-18 %9 Review %# %! Pre-training in Recommendation %* %< %T Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect %U https://www.frontiersin.org/articles/10.3389/fdata.2021.602071 %V 4 %0 JOURNAL ARTICLE %@ 2624-909X %X Recommender systems aim to provide item recommendations for users and are usually faced with data sparsity problems (e.g., cold start) in real-world scenarios. Recently pre-trained models have shown their effectiveness in knowledge transfer between domains and tasks, which can potentially alleviate the data sparsity problem in recommender systems. In this survey, we first provide a review of recommender systems with pre-training. In addition, we show the benefits of pre-training to recommender systems through experiments. Finally, we discuss several promising directions for future research of recommender systems with pre-training. The source code of our experiments will be available to facilitate future research.