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.

162 papers of 4,574 · showing 151–162Sort Recent · Most cited
  1. 2019PDF ↗
  2. 2019
    Online Meta-LearningChelsea Finn, Aravind Rajeswaran, Sham M. Kakade, Sergey LevineICML · Stanford University · University of Washington · +3
    PDF ↗
  3. 2019
    Policy Consolidation for Continual Reinforcement LearningChristos Kaplanis, Murray Shanahan, Claudia ClopathICML · Imperial College London
    PDF ↗
  4. 2018
    Towards Robust Evaluations of Continual LearningSebastian Farquhar, Yarin GalICML · University of Oxford
    PDF ↗
  5. 2018
    Progress & Compress : A scalable framework for continual learningJonathan Schwarz, Jelena Luketina, Wojciech Marian Czarnecki … Raia HadsellICML
    PDF ↗
  6. 2018
    Differentiable plasticity: training plastic neural networks with backpropagationThomas Miconi, Jeff Clune, Kenneth O. StanleyICML · Neurosciences Institute · University of Wyoming · +1
    PDF ↗
  7. 2018
    Continual Reinforcement Learning with Complex SynapsesChristos Kaplanis, Murray Shanahan, Claudia ClopathICML · Imperial College London
    PDF ↗
  8. 2018
    Overcoming catastrophic forgetting with hard attention to the taskJoan Serrà, Dídac Surís, Marius Miron, Alexandros KaratzoglouICML
    PDF ↗
  9. 2017
    Meta NetworksTsendsuren Munkhdalai, Hong YuICML
    PDF ↗
  10. 2017
    Differentiable Programs with Neural LibrariesAlexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel TarlowICML · Microsoft (United States)
    PDF ↗
  11. 2015
    Safe Policy Search for Lifelong Reinforcement Learning with Sublinear RegretHaitham Bou Ammar, Rasul Tutunov, Eric EatonICML · University of Pennsylvania
    PDF ↗
  12. 2014
    A PAC-Bayesian bound for Lifelong LearningAnastasia Pentina, Christoph H. LampertICML · Institute of Science and Technology Austria
    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.