Related work

The foundational work on continual learning, 1989 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

8 papers of 5,456Sort Recent · Most cited
  1. 2021
    CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future DirectionsVincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodríguez … Davide MaltoniArtificial Intelligence · University of Bologna · Mila - Quebec Artificial Intelligence Institute · +7
    PDF ↗
  2. 2021
    Powerpropagation: A sparsity inducing weight reparameterisationJonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu … Yee Whye TehNeurIPS · Google (United States)
    PDF ↗
  3. 2021
    Continual World: A Robotic Benchmark For Continual Reinforcement LearningMaciej Wołczyk, Michał Zając, Razvan Pascanu … Piotr MiłośNeurIPS · Jagiellonian University · Google (United States)
    PDF ↗
  4. 2021
    Continual Learning for Text Classification with Information Disentanglement Based RegularizationYufan Huang, Yanzhe Zhang, Jiaao Chen … Diyi YangNAACL · Georgia Institute of Technology · Google (United States) · +1
    PDF ↗
  5. 2021
    Towards Continual Learning for Multilingual Machine Translation via Vocabulary SubstitutionXavier García, Noah Constant, Ankur P. Parikh, Orhan FıratNAACL · Google (United States)
    PDF ↗
  6. 2021
    Reset-Free Lifelong Learning with Skill-Space PlanningKevin Lü, Aditya Grover, Pieter Abbeel, Igor MordatchICLR · University of California, Berkeley · Stanford University · +1
    PDF ↗
  7. 2021
    Linear Mode Connectivity in Multitask and Continual LearningSeyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür … Hassan GhasemzadehICLR · Washington State University · Google (United States)
    PDF ↗
  8. 2021
    Anatomy of Catastrophic Forgetting: Hidden Representations and Task SemanticsVinay Ramasesh, Ethan Dyer, Maithra RaghuICLR · Google (United States) · Cornell University
    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 written by someone who has published there, or cited a few hundred times. 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.