{"id":11563737,"url":"https://github.com/fajieyuan/universal_user_representation","last_synced_at":"2025-10-03T14:30:59.243Z","repository":{"id":109005254,"uuid":"440439910","full_name":"fajieyuan/universal_user_representation","owner":"fajieyuan","description":"papers of universal user representation learning for recommendation","archived":false,"fork":false,"pushed_at":"2024-03-01T13:28:00.000Z","size":58,"stargazers_count":22,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-09-29T14:31:50.768Z","etag":null,"topics":["bert","catastrophic-forgetting","cold-start","continual-learning","cross-domain-recommendation","general-purpose","item-recommendation","lifelong-learning","multi-domain-recommendation","pre-training","pruning","recommender-system","representation-learning","transfer","transfer-learning","transformer","trimming","user-modeling","user-profiling","user-representation"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fajieyuan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2021-12-21T08:13:46.000Z","updated_at":"2024-09-25T02:21:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"0a171354-f31e-44bc-b9aa-d0d22198ca03","html_url":"https://github.com/fajieyuan/universal_user_representation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fajieyuan%2Funiversal_user_representation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fajieyuan%2Funiversal_user_representation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fajieyuan%2Funiversal_user_representation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fajieyuan%2Funiversal_user_representation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fajieyuan","download_url":"https://codeload.github.com/fajieyuan/universal_user_representation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235139110,"owners_count":18942108,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert","catastrophic-forgetting","cold-start","continual-learning","cross-domain-recommendation","general-purpose","item-recommendation","lifelong-learning","multi-domain-recommendation","pre-training","pruning","recommender-system","representation-learning","transfer","transfer-learning","transformer","trimming","user-modeling","user-profiling","user-representation"],"created_at":"2024-06-23T05:59:13.718Z","updated_at":"2025-10-03T14:30:58.918Z","avatar_url":"https://github.com/fajieyuan.png","language":null,"funding_links":[],"categories":["Universal Representation Learning"],"sub_categories":["Perspective"],"readme":"# Universal_user_representations for recommendation\n## Move to this New Link： https://github.com/westlake-repl/Recommendation-Systems-without-Explicit-ID-Features-A-Literature-Review\n\nPapers of universal user representations (lifelong) learning for item recommendations https://zhuanlan.zhihu.com/p/437671278 （ 以下内容参考知乎: 推荐系统通用用户表征预训练与迁移学习研究进展）\n\n## Four Large-scale Recommendation datasets for evaluating cross-domain recommendation models or transferable recommendaiton models\n\n(1) PixelRec: https://github.com/westlake-repl/PixelRec\n\n(2) NineRec: https://github.com/westlake-repl/NineRec\n\n(3) MicroLens: https://github.com/westlake-repl/MicroLens\n\n(4) Tenrec: https://github.com/yuangh-x/2022-NIPS-Tenrec\n\n## Our research papers that apply pre-training and transfer learning to learn universal user representations for recommender systems:\n\n1 Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation SIGIR2020 https://arxiv.org/abs/2001.04253 \n\nWith github codes and datasets: https://github.com/fajieyuan/SIGIR2020_peterrec\n\nKeywords: self-supervised learning, user sequential behaviors, pretraining, transfer learning, universal user representation, user profile prediction, cold-start problem\n\n(1) We are the first to evidence that self-supervised user behavior pre-training helps many downstream tasks.\n\n(2) We are also the first to provide user profile prediction as a way to assess the universal or generic property of user representation\n\n(3) We release a large-scale public dataset for user representation transer learning and source code.\n\n2 One Person, One Model, One World: Learning Continual User Representation without Forgetting SIGIR2021 https://arxiv.org/abs/2009.13724 \n\nWith github codes and datasets: https://github.com/fajieyuan/SIGIR2021_Conure\n\nKeywords: self-supervised learning, lifelong learning, pre-training, transfer learning, fine-tuning,  general-purpose user representation, user profile prediction, cold-start recommendation\n\n(1) We are the first to propose universal lifelong user representation learning mechanism for recommender system\n\n(2) We are the first to clearly demonstrate the catastrophic forgetting and over-parameterization issues in recommender sytem.\n\n(3) We release the dataset for lifelong user representation learning and source code.\n\n3 Learning Transferable User Representations with Sequential Behaviors via Contrastive Pre-training ICDM2021 https://fajieyuan.github.io/papers/ICDM2021.pdf\n\nKeywords: contrative learnng, self-supervised learning, transfer learning, pretraining, finetuning,  general-purpose user representation, user profile prediction, cold-start problem\n\n4 User-specific Adaptive Fine-tuning for Cross-domain Recommendations TKDE2021 https://arxiv.org/pdf/2106.07864.pdf\n\nKeywords: adaptive fine-tuning, pre-training, cold-start problem, cross-domain recommendation,  general-purpose  user representation\n\n\n5 Transrec: learning transferable recommendation from mixture-of-modality feedback  https://arxiv.org/pdf/2206.06190.pdf\n\nKeywords: foundation recommendation models, pre-training, transfer learning, mixture-of-modality, content-based recommendation\n\n## A large-scale pre-training dataset for learning universal user representations and evaluations\n\nhttps://github.com/fajieyuan/recommendation_dataset_pretraining\n\n##  Other papers about universal user representations:\n\n1 Scaling Law for Recommendation Models: Towards General-purpose User Representations  NAVER CLOVA 2021\n\n2 One4all User Representation for Recommender Systems in E-commerce NAVER CLOVA 2021\n\n3 Knowledge Transfer via Pre-training for Recommendation Tsinghua University 2021 frontiers\n\n4 Self-supervised Learning for Large-scale Item Recommendations Google 2021\n\n5 UserBERT: Self-supervised User Representation Learning Reject by ICLR2021\n\n6 UPRec: User-Aware Pre-training for Recommender Systems AAAI2021\n\n7 Personalized Transfer of User Preferences for Cross-domain Recommendation WSDM2022\n\n8 Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks Ailabab KDD2019\n\n9 Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation\n\n10 Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt \u0026 Predict Paradigm (P5)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffajieyuan%2Funiversal_user_representation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffajieyuan%2Funiversal_user_representation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffajieyuan%2Funiversal_user_representation/lists"}