Move to https://github.com/westlake-repl/Recommendation-Systems-without-Explicit-ID-Features-A-Literature-Review
Four Large-scale Recommendation datasets for evaluating foundation recommendation models or transferable recommendaiton models
(1) PixelRec: https://github.com/westlake-repl/PixelRec
(2) NineRec: https://github.com/westlake-repl/NineRec
(3) MicroLens: https://github.com/westlake-repl/MicroLens
(4) Tenrec: https://github.com/yuangh-x/2022-NIPS-Tenrec
learning universal user representation with lifelong learning mechanism for recommender systems
We list several papers in the recommendation field that learning universal user representations that support lifelong or continual learning.
1 One Person, One Model, One World: Learning Continual User Representation without Forgetting.
Publications of SIGIR2021 https://arxiv.org/abs/2009.13724
Code & Dataset: https://github.com/fajieyuan/SIGIR2021_Conure
Keywords: lifelong learning, universal user representations, pretraining, transfer learning, finetuning, user profile prediction, cold-start problem
2 Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation
Publications of SIGIR2020 https://arxiv.org/abs/2001.04253
Code & Dataset: https://github.com/fajieyuan/SIGIR2020_peterrec
Keywords: self-supervised learning, user behaviors, pre-training, transfer learning, user representation, user profile prediction, cold-start problem
3 Scaling Law for Recommendation Models: Towards General-purpose User Representations
https://arxiv.org/pdf/2111.11294.pdf
Keywords: general-purpose user representation learning, recommender systems, GPT, BERT, Self-Supervised Lifelong learning, Contrastive Learning, transfer learning
4 Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training
Publications of ICDM2021 https://fajieyuan.github.io/papers/ICDM2021.pdf
Keywords: general-purpose user representation learning, recommender systems, Self-Supervised Lifelong learning, Contrastive Learning, transfer learning，user behaviors