Related work

The foundational work on continual learning, 1991 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

4,574 papers · showing 3801–3850Sort Recent · Most cited
  1. 2021
    CLeaR: An adaptive continual learning framework for regression tasksYujiang He, Bernhard SickAI Perspectives · University of Kassel
    PDF ↗
  2. 2021
    ACAE-REMIND for Online Continual Learning with Compressed Feature ReplayKai Wang, Joost van de Weijer, Luis HerranzPattern Recognition Letters · Universitat Autònoma de Barcelona · Computer Vision Center
    PDF ↗
  3. 2021
    Algorithmic insights on continual learning from fruit fliesYang Shen, Sanjoy Dasgupta, Saket NavlakhaarXiv
    PDF ↗
  4. 2021
    AlterSGD: Finding Flat Minima for Continual Learning by Alternative TrainingZhongzhan Huang, Mingfu Liang, Senwei Liang, Wei HearXiv · Purdue University West Lafayette · Nanyang Technological University
    PDF ↗
  5. 2021
    Kernel Continual LearningMahammad Mahdi Derakhshani, Xiantong Zhen, Ling Shao, Cees G. M. SnoekICML · University of Amsterdam · Inception Institute of Artificial Intelligence
    PDF ↗
  6. 2021
    One Person, One Model, One World: Learning Continual User Representation without ForgettingFajie Yuan, Guoxiao Zhang, Alexandros Karatzoglou … Yudong LiENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) · Tencent (China) · Westlake University · +2
    PDF ↗
  7. 2021
    TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph CompletionJiapeng Wu, Yishi Xu, Yingxue Zhang … Jackie Chi Kit CheungSIGIR · McGill University · Université de Montréal · +1
    PDF ↗
  8. 2021
    Continual Learning for Class- and Domain-Incremental Semantic SegmentationTobias Kalb, Masoud Roschani, Miriam Ruf, Jürgen BeyererIEEE Intelligent Vehicles Symposium (IV) · Fraunhofer Institute of Optronics, System Technologies and Image Exploitation · Karlsruhe Institute of Technology
    PDF ↗
  9. 2021
    Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment ClassificationBinzong Geng, Min Yang, Fajie Yuan … Ruifeng XuSIGIR · University of Science and Technology of China · Chinese Academy of Sciences · +5
    PDF ↗
  10. 2021PDF ↗
  11. 2021
    Continual Learning in the Teacher-Student Setup: Impact of Task SimilaritySebastian Lee, Sebastian Goldt, Andrew SaxeICML · Microsoft Research (United Kingdom) · Scuola Internazionale Superiore di Studi Avanzati · +1
    PDF ↗
  12. 2021
    A Fixed Version of Quadratic Program in Gradient Episodic MemoryWei Zhou, Yiying LiarXiv · National University of Defense Technology
    PDF ↗
  13. 2021
    FoCL: Feature-Oriented Continual Learning for Generative ModelsQicheng Lao, Mehrzad Mortazavi, Marzieh S. Tahaei … Mohammad HavaeiPattern Recognition · Sichuan University · West China Medical Center of Sichuan University · +3
    PDF ↗
  14. 2021
    Learning Then, Learning Now, and Every Second in Between: Lifelong Learning With a Simulated Humanoid RobotAleksej Logacjov, Matthias Kerzel, Stefan WermterFrontiers · Universität Hamburg
    PDF ↗
  15. 2021
    Tackling Catastrophic Forgetting and Background Shift in Continual Semantic SegmentationArthur Douillard, Yifu Chen, Arnaud Dapogny, Matthieu CordarXiv · Valeo (France)
    PDF ↗
  16. 2022
    Lifelong Teacher-Student Network LearningFei Ye, Adrian G. BorşTPAMI · University of York
    PDF ↗
  17. 2021
    Task-agnostic Continual Learning with Hybrid Probabilistic ModelsPolina Kirichenko, Mehrdad Farajtabar, Dushyant Rao … Razvan PascanuarXiv
    PDF ↗
  18. 2022
    Continual Novelty DetectionRahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin, Richard E. TurnerCoLLAs
    PDF ↗
  19. 2021
    SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental LearningSungmin Cha, Beomyoung Kim, Youngjoon Yoo, Taesup MoonNeurIPS · Sungkyunkwan University · Naver (South Korea) · +1
    PDF ↗
  20. 2021
    On the importance of cross-task features for class-incremental learningAlbin Soutif--Cormerais, Marc Masana, Joost van de Weijer, Bartłomiej TwardowskiarXiv
    PDF ↗
  21. 2022
    Incremental Deep Neural Network Learning Using Classification Confidence ThresholdingJustin Leo, Jugal KalitaTNNLS · University of Colorado Colorado Springs
    PDF ↗
  22. 2021
    Natural continual learning: success is a journey, not (just) a destinationTa-Chu Kao, Kristopher T. Jensen, Gido M. van de Ven … Guillaume HennequinNeurIPS
    PDF ↗
  23. 2022
    Learngene: From Open-World to Your Learning TaskQiufeng Wang, Xin Geng, Shuxia Lin … Ning XuAAAI
    PDF ↗
  24. 2021
    A Novel Approach to Lifelong Learning: The Plastic Support StructureGeorges Kanaan, Kai Wen Zheng, Lucas FenauxarXiv · University of Toronto
    PDF ↗
  25. 2021
    Optimizing Reusable Knowledge for Continual Learning via MetalearningJulio Hurtado, Alain Raymond-Sáez, Álvaro SotoNeurIPS · Pontificia Universidad Católica de Chile
    PDF ↗
  26. 2021
    Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic ForgettingZeke Xie, Fengxiang He, Shaopeng Fu … Masashi SugiyamaNeural Computation · RIKEN Center for Advanced Intelligence Project · The University of Tokyo · +1
    PDF ↗
  27. 2021
    Lifelong Personalization via Gaussian Process Modeling for Long-Term HRISamuel Spaulding, Jocelyn Shen, Hae Won Park, Cynthia BreazealFrontiers · Massachusetts Institute of Technology
    PDF ↗
  28. 2021
    Energy Aligning for Biased ModelsBowen Zhao, Chen Chen, Qi Ju, Shu‐Tao XiaarXiv
    PDF ↗
  29. 2022PDF ↗
  30. 2021
    Knowing when we do not know: Bayesian continual learning for sensing-based analysis tasksSandra Servia-Rodríguez, Cecilia Mascolo, Young D. KwonarXiv
    PDF ↗
  31. 2021
    ModelCI-e: Enabling Continual Learning in Deep Learning Serving SystemsYizheng Huang, Huaizheng Zhang, Yonggang Wen … Ta Nguyen Binh DuongarXiv
    PDF ↗
  32. 2021
    Fast On-Device Adaptation for Spiking Neural Networks Via Online-Within-Online Meta-LearningBleema Rosenfeld, Bipin Rajendran, Osvaldo SimeoneIEEE Data Science and Learning Workshop (DSLW) · New Jersey Institute of Technology · King's College London
    PDF ↗
  33. 2021
    Solving hybrid machine learning tasks by traversing weight space geodesicsGuruprasad Raghavan, Matt ThomsonarXiv · California Institute of Technology
    PDF ↗
  34. 2021
    A Procedural World Generation Framework for Systematic Evaluation of Continual LearningTimm Hess, Martin Mundt, Iuliia Pliushch, Visvanathan RameshNeurIPS · Goethe University Frankfurt
    PDF ↗
  35. 2021
    Continual Learning in Deep Networks: an Analysis of the Last LayerTimothée Lesort, Thomas George, Irina RisharXiv
    PDF ↗
  36. 2022
    Online Coreset Selection for Rehearsal-based Continual LearningJaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju HwangICLR · Korea Advanced Institute of Science and Technology · Korea Institute of Science and Technology
    PDF ↗
  37. 2022
    Using top-down modulation to optimally balance shared versus separated task representationsPieter Verbeke, Tom VergutsNeural Networks · Ghent University Hospital
    PDF ↗
  38. 2021
    Personalizing Pre-trained ModelsMina Khan, P. Srivatsa, Advait Rane … Pattie MaesarXiv
    PDF ↗
  39. 2021
    DER: Dynamically Expandable Representation for Class Incremental LearningShipeng Yan, Jiangwei Xie, Xuming HeCVPR · ShanghaiTech University · Shanghai Institute of Microsystem and Information Technology · +1
    PDF ↗
  40. 2021
    Rainbow Memory: Continual Learning with a Memory of Diverse SamplesJihwan Bang, Heesu Kim, Youngjoon Yoo … Jonghyun ChoiCVPR · NAVER Cloud (South Korea) · Naver (South Korea) · +1
    PDF ↗
  41. 2021
    Few-Shot Incremental Learning with Continually Evolved ClassifiersChi Zhang, Nan Song, Guosheng Lin … Yinghui XuCVPR · Nanyang Technological University · Alibaba Group (Cayman Islands)
    PDF ↗
  42. 2021
    PLOP: Learning without Forgetting for Continual Semantic SegmentationArthur Douillard, Yifu Chen, Arnaud Dapogny, Matthieu CordCVPR · Sorbonne Université · Laboratoire Médiations · +1
    PDF ↗
  43. 2021
    Adaptive Aggregation Networks for Class-Incremental LearningYaoyao Liu, Bernt Schiele, Qianru SunCVPR · Max Planck Institute for Informatics · Singapore Management University
    PDF ↗
  44. 2021PDF ↗
  45. 2021
    Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental LearningAli Cheraghian, Shafin Rahman, Pengfei Fang … Mehrtash HarandiCVPR · Australian National University · Commonwealth Scientific and Industrial Research Organisation · +3
    PDF ↗
  46. 2021
    Training Networks in Null Space of Feature Covariance for Continual LearningShipeng Wang, Xiaorong Li, Jian Sun, Zongben XuCVPR · Xi'an Jiaotong University
    PDF ↗
  47. 2021
    Avalanche: an End-to-End Library for Continual LearningVincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu … Davide MaltoniCVPR · University of Pisa · University of Bologna · +12
    PDF ↗
  48. 2021
    Distilling Causal Effect of Data in Class-Incremental LearningXinting Hu, Kaihua Tang, Chunyan Miao … Hanwang ZhangCVPR · Nanyang Technological University · Alibaba Group (Cayman Islands)
    PDF ↗
  49. 2021
    Self-Promoted Prototype Refinement for Few-Shot Class-Incremental LearningKai Zhu, Yang Cao, Wei Zhai … Zheng-Jun ZhaCVPR · University of Science and Technology of China · Huawei Technologies (United Kingdom)
    PDF ↗
  50. 2021PDF ↗
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It lists only papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or led by someone who has published there, or cited a few hundred times, and only papers with a PDF we can point you at, so every title opens the paper itself. Preprints that later get accepted, and authors who later publish at those venues, are picked up by the weekly run. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.