/lifelong_learning_user_representation

learning universal user representation with lifelong learning mechanism for recommender systems

Papers of lifelong_universal_user_representations for recommendation

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 learningļ¼Œuser behaviors