cross-domain recommendation,transfer learning,pre-training,self-supervise learning, contrastive learning,cold-start recommendation,user profile prediction.
1 Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation SIGIR2020 https://arxiv.org/abs/2001.04253 (Tencent+Google)
Github:https://github.com/fajieyuan/SIGIR2020_peterrec
Keywords: self-supervise learning, user sequential behaviors, pretraining, transfer learning, user representation, user profile prediction, cold-start problem
2 One Person, One Model, One World: Learning Continual User Representation without Forgetting SIGIR2021 https://arxiv.org/abs/2009.13724 (Westlake+Tencent+Google)
Keywords: self-supervise learning, lifelong learning, pretraining, transfer learning, finetuning, user representation, user profile prediction, cold-start problem
Github:https://github.com/fajieyuan/SIGIR2021_Conure
3 Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training ICDM2021 https://fajieyuan.github.io/papers/ICDM2021.pdf (Tencent)
Keywords: contrative learnng, self-supervise learning, transfer learning, pretraining, finetuning, user representation, user profile prediction, cold-start problem
4 User-specific Adaptive Fine-tuning for Cross-domain Recommendations TKDE2021 https://arxiv.org/pdf/2106.07864.pdf(Tencent)
Keywords: adaptive finetuning, pretraining, cold-start problem, cross-domain recommendation
5 TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback (Westlake) ID-agnostic
Keywords: tranfer learning, pre-training, mixture-of-modality, content-based recommendation, general-purpose recommender system
We have also released large-scale dataset (over 1 million user clicking behaviors) for performing transfer learning of user preference in recommendation field
https://github.com/fajieyuan/recommendation_dataset_pretraining
1 Knowledge Transfer via Pre-training for Recommendation Tsinghua University 2021 frontiers
2 One4all User Representation for Recommender Systems in E-commerce NAVER CLOVA 2021
3 One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction CIKM2021 Ailabab
4 AutoFT: Automatic Fine-Tune for Parameters Transfer Learning in Click-Through Rate Prediction Huawei 2021
5 Self-supervised graph learning for recommendation
6 DaRE: A Cross-Domain Recommender System with Domain-aware Feature Extraction and Review Encoder 2021
7 Self-supervised Learning for Large-scale Item Recommendations Google 2021
8 UserBERT: Self-supervised User Representation Learning Reject by ICLR2021
9 UPRec: User-Aware Pre-training for Recommender Systems AAAI2021
10 Cross Domain Recommendation Systems using Deep Learning
11 Personalized Transfer of User Preferences for Cross-domain Recommendation WSDM2022
12 Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks Ailabab KDD2019
13 Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
14 Self-supervised Graph Learning for Recommendation
15 Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-N Recommendation
16 Towards Universal Sequence Representation Learning for Recommender Systems