Paper List： https://github.com/westlake-repl/Recommendation-Systems-without-Explicit-ID-Features-A-Literature-Review
推荐系统预训练pre-training+跨域推荐、迁移学习场景大规模数据集（开源） A Large-scale Dataset for Transfer Learning and Pre-training in Recommendation.
数据集：包括腾讯看点和QQ浏览器的短视频视频、新闻和广告用户点击观看行为，拥有shared user数据，因此可以用于用户表征建模和迁移学习，跨域推荐，冷启动等场景，同时数据集包含了用户的画像信息，因为可以用于基于迁移学习的画像预测，详情见以下参考论文和数据集readme文件。 DataSets links for recommender systems research, in particular for transfer learning, pre-training, lifelong learning, cold start recommendation, cross-domain recommendation
https://github.com/fajieyuan/recommendation_dataset_pretraining 文献1
https://drive.google.com/open?id=1OcvbBJN0jlPTEjE0lvcDfXRkzOjepMXH 文献2
注: 文献1和文献2数据集来自同一套原始数据。文献1点击和点赞行为进行了区分。
参考文献： 1） One Person, One Model, One World: Learning Continual User Representation without Forgetting. SIGIR2021. Yuan, Fajie and Zhang, Guoxiao and Karatzoglou, Alexandros and Jose, Joemon and Kong, Beibei and Li, Yudong. Github: https://github.com/fajieyuan/SIGIR2020_peterrec
2） Parameter-efficient transfer from sequential behaviors for user modeling and recommendation. SIGIR2020. Yuan, Fajie and He, Xiangnan and Karatzoglou, Alexandros and Zhang, Liguang. Github: https://github.com/fajieyuan/SIGIR2021_Conure
3） Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training. ICDM2021. Cheng, Mingyue and Yuan, Fajie and Liu, Qi and Xin, Xin and Chen, Enhong
4） User-specific Adaptive Fine-tuning for Cross-domain Recommendation. TKDE2021. Chen, Lei and Yuan, Fajie and Yang, Jiaxi and He, Xiangnan and Li, Chengming and Yang, Min.