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 4251–4300Sort Recent · Most cited
  1. 2020
    Findings of the First Shared Task on Lifelong Learning Machine TranslationLoïc Barrault, Magdalena Biesialska, Marta R. Costa‐jussà … Olivier GalibertEMNLP · University of Sheffield · Universitat Politècnica de Catalunya · +2
    PDF ↗
  2. 2020
    Morphology dictates learnability in neural controllersJoshua Powers, Ryan Grindle, Sam Kriegman … Josh BongardThe 2020 Conference on Artificial Life · University of Vermont
    PDF ↗
  3. 2020
    Confidence Calibration for Incremental LearningDongmin Kang, Yeonsik Jo, Yeongwoo Nam, Jonghyun ChoiIEEE Access · Gwangju Institute of Science and Technology
    PDF ↗
  4. 2020
    Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization MethodsYifan Chang, Wenbo Li, Jian Peng … Yingliang HuangIEEE Access · University of Science and Technology of China · Hefei Institute of Technology Innovation · +3
    PDF ↗
  5. 2019
    Side-Tuning: Network Adaptation via Additive Side NetworksJeffrey O. Zhang, Alexander F. Sax, Amir Zamir … Jitendra MalikarXiv
    PDF ↗
  6. 2021
    Direction Concentration Learning: Enhancing Congruency in Machine LearningYan Luo, Yongkang Wong, Mohan Kankanhalli, Qi ZhaoTPAMI · University of Minnesota · National University of Singapore
    PDF ↗
  7. 2019
    Incremental Learning in Deep Convolutional Neural Networks Using Partial Network SharingSyed Shakib Sarwar, Aayush Ankit, Kaushik RoyIEEE Access · Purdue University West Lafayette
    PDF ↗
  8. 2020
    Continuous Meta-Learning without TasksJ. Michael Harrison, Apoorva Sharma, Chelsea Finn, Marco PavoneNeurIPS · Stanford University · University of California, Berkeley
    PDF ↗
  9. 2019PDF ↗
  10. 2019
    Continual Learning for RoboticsTimothée Lesort, Vincenzo Lomonaco, Andrei Stoian … Natalia Díaz-RodríguezInformation Fusion · Thales (Portugal) · Institut national de recherche en sciences et technologies du numérique · +3
    PDF ↗
  11. 2019
    Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement LearningJoão G. Ribeiro, Francisco S. Melo, João DiasEPiC series in computing · Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento
    PDF ↗
  12. 2019PDF ↗
  13. 2019
    Learning Sparse Representations Incrementally in Deep Reinforcement LearningJ. Fernando Hernandez-Garcia, Richard S. SuttonarXiv · University of Alberta
    PDF ↗
  14. 2019
    Bayesian Structure Adaptation for Continual LearningAbhishek Kumar, Sunabha Chatterjee, Piyush RaiarXiv · Indian Institute of Technology Kanpur
    PDF ↗
  15. 2019
    Regularization Shortcomings for Continual LearningTimothée Lesort, Andrei Stoian, Filliat, DavidarXiv · École d'Ingénieurs en Chimie et Sciences du Numérique · Thales (Portugal)
    PDF ↗
  16. 2021
    Hierarchical Indian buffet neural networks for Bayesian continual learningSamuel Kessler, Vu Nguyen, Stefan Zohren, Stephen RobertsUAI · University of Oxford · Science Oxford
    PDF ↗
  17. 2021
    Overcoming Catastrophic Forgetting by Bayesian Generative RegularizationPatrick H. Chen, Wei Wei, Cho‐Jui Hsieh, Bo DaiICML · University of California, Los Angeles
    PDF ↗
  18. 2019
    Incremental learning for the detection and classification of GAN-generated imagesFrancesco Marra, Cristiano Saltori, Giulia Boato, Luisa VerdolivaInternational Workshop on Information Forensics and Security · Federico II University Hospital · University of Trento
    PDF ↗
  19. 2019
    Single-Net Continual Learning with Progressive Segmented TrainingXiaocong Du, Gouranga Charan, Frank Liu, Yu CaoICML · Arizona State University · Oak Ridge National Laboratory
    PDF ↗
  20. 2019
    Frosting Weights for Better Continual TrainingXiaofeng Zhu, Feng Liu, Goce Trajcevski, Dingding WangICML · Northwestern University · Florida Atlantic University · +1
    PDF ↗
  21. 2019
    AutoML @ NeurIPS 2018 challenge: Design and ResultsHugo Jair Escalante, Wei-Wei Tu, Isabelle Guyon … Qiang YangMachine Learning · Gleason (United States) · National Institute of Astrophysics, Optics and Electronics · +8
    PDF ↗
  22. 2019
    Challenges in Task Incremental Learning for Assistive RoboticsFan Feng, Rosa H. M. Chan, Xuesong Shi … Qi SheIEEE Access · City University of Hong Kong
    PDF ↗
  23. 2019
    GRIm-RePR: Prioritising Generating Important Features for Pseudo-RehearsalC. Atkinson, Brendan McCane, Lech Szymanski, Anthony RobinsarXiv
    PDF ↗
  24. 2020
    Continual Learning with Adaptive Weights (CLAW)Tameem Adel, Han Zhao, Richard E. TurnerICLR
    PDF ↗
  25. 2019
    A Unified Framework for Lifelong Learning in Deep Neural NetworksCharles X. Ling, Tanner BohnarXiv · Western University
    PDF ↗
  26. 2019
    Online Learned Continual Compression with Stacked Quantization ModuleLucas Caccia, Eugene Belilovsky, M. Caccia, Joëlle PineauarXiv · McGill University · Meta (Israel)
    PDF ↗
  27. 2019PDF ↗
  28. 2019
    Lifelong Learning in Costly Feature SpacesMaria-Florina Balcan, Avrim Blum, Vaishnavh NagarajanTheoretical Computer Science · Carnegie Mellon University · Toyota Technological Institute at Chicago
    PDF ↗
  29. 2019
    Task-adaptive incremental learning for intelligent edge devicesZhuwei Qin, Fuxun Yu, Xiang ChenACM/IEEE Symposium on Edge Computing · George Mason University
    PDF ↗
  30. 2019
    Automatic Construction of Multi-layer Perceptron Network from Streaming ExamplesMahardhika Pratama, Choiru Za’in, Andri Ashfahani … Weiping DingCIKM · Nanyang Technological University · La Trobe University · +1
    PDF ↗
  31. 2019
    Continual Unsupervised Representation LearningDushyant Rao, Francesco Visin, Andrei Rusu … Raia HadsellNeurIPS · Carnegie Mellon University · Google (United States) · +2
    PDF ↗
  32. 2019
    Continual Multi-task Gaussian ProcessesPablo Moreno-Muñoz, Antonio Artés-Rodrı́guez, Mauricio A. ÁlvarezarXiv · Universidad Carlos III de Madrid · University of Sheffield
    PDF ↗
  33. 2019PDF ↗
  34. 2019
    Overcoming Forgetting in Federated Learning on Non-IID DataNeta Shoham, Tomer Avidor, Aviv Keren … Itai ZeitakarXiv
    PDF ↗
  35. 2020
    Orthogonal Gradient Descent for Continual LearningMehrdad Farajtabar, Navid Azizan, A. Mott, Ang LiAISTATS · Google (United States)
    PDF ↗
  36. 2019
    Compacting, Picking and Growing for Unforgetting Continual LearningSteven C. Y. Hung, Cheng-Hao Tu, Cheng‐En Wu … Chu-Song ChenNeurIPS
    PDF ↗
  37. 2019
    Uncertainty-based modulation for lifelong learningAndrew Brna, Ryan C. Brown, Patrick Connolly … Mario Aguilar-SimonNeural Networks · Triangle · Teledyne Technologies (United States)
    PDF ↗
  38. 2019
    Learning to Remember from a Multi-Task TeacherYuwen Xiong, Mengye Ren, Raquel UrtasunarXiv
    PDF ↗
  39. 2019PDF ↗
  40. 2019
    Is Fast Adaptation All You Need?Khurram Javed, Hengshuai Yao, Martha WhitearXiv · University of Alberta · Huawei Technologies (China)
    PDF ↗
  41. 2019
    Incremental Learning Techniques for Semantic SegmentationUmberto Michieli, Pietro ZanuttighICCV · University of Padua
    PDF ↗
  42. 2019
    Overcoming Catastrophic Forgetting With Unlabeled Data in the WildKibok Lee, Kimin Lee, Jinwoo Shin, Honglak LeeICCV · Korea Advanced Institute of Science and Technology · University of Michigan · +1
    PDF ↗
  43. 2019
    Lifelong GAN: Continual Learning for Conditional Image GenerationMengyao Zhai, Lei Chen, Fred Tung … Greg MoriICCV · Simon Fraser University · Borealis (Austria)
    PDF ↗
  44. 2019
    ACE: Adapting to Changing Environments for Semantic SegmentationZuxuan Wu, Xin Wang, Joseph E. Gonzalez … Larry S. DavisICCV · Berkeley College · University of California, Berkeley · +1
    PDF ↗
  45. 2019
    Continual Learning by Asymmetric Loss Approximation With Single-Side OverestimationDong-Min Park, Seokil Hong, Bohyung Han, Kyoung Mu LeeICCV · Seoul National University · Samsung (South Korea)
    PDF ↗
  46. 2019
    Continual Learning of New Sound Classes Using Generative ReplayZhepei Wang, Cem Subakan, Efthymios Tzinis … Laurent CharlinIEEE Workshop on Applications of Signal Processing to Aud… · University of Illinois Urbana-Champaign · Mila - Quebec Artificial Intelligence Institute
    PDF ↗
  47. 2019
    From Crystallized Adaptivity to Fluid Adaptivity in Deep Reinforcement Learning — Insights from Biological Systems on Adaptive FlexibilityMalte Schilling, Helge Ritter, Frank W. OhlIEEE International Conference on Systems, Man and Cyberne… · Bielefeld University · Otto-von-Guericke-Universität Magdeburg · +1
    PDF ↗
  48. 2019PDF ↗
  49. 2019
    Learning with Long-term Remembering: Following the Lead of Mixed Stochastic GradientYunhui Guo, Mingrui Liu, Tianbao Yang, Tajana RosingarXiv · University of California San Diego · University of Iowa
    PDF ↗
  50. 2020
    Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learningDeboleena Roy, Priyadarshini Panda, Kaushik RoyNeural Networks · Purdue University West Lafayette
    PDF ↗
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.