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 4501–4550Sort Recent · Most cited
  1. 2018
    FearNet: Brain-Inspired Model for Incremental LearningRonald Kemker, Christopher KananICLR
    PDF ↗
  2. 2017
    Gradual Tuning: a better way of Fine Tuning the parameters of a Deep Neural NetworkGuglielmo Montone, J. Kevin Ο’Regan, Alexander V. TerekhovarXiv
    PDF ↗
  3. 2017
    Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple TaskGuglielmo Montone, J. Kevin Ο’Regan, Alexander V. TerekhovarXiv
    PDF ↗
  4. 2018
    Modular Continual Learning in a Unified Visual EnvironmentKevin Feigelis, Blue Sheffer, Daniel YaminsICLR · Rutgers, The State University of New Jersey · Stanford University
    PDF ↗
  5. 2017
    Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networksRoby Velez, Jeff ClunePLOS · University of Wyoming · Uber AI (United States)
    PDF ↗
  6. 2017
    ASP: Learning to Forget With Adaptive Synaptic Plasticity in Spiking Neural NetworksPriyadarshini Panda, Jason M. Allred, Shriram Ramanathan, Kaushik RoyIEEE Journal on Emerging and Selected Topics in Circuits… · Purdue University West Lafayette
    PDF ↗
  7. 2017PDF ↗
  8. 2017
    Incremental Learning of Object Detectors without Catastrophic ForgettingKonstantin Shmelkov, Cordelia Schmid, Karteek AlahariICCV · Institut polytechnique de Grenoble · Centre National de la Recherche Scientifique · +3
    PDF ↗
  9. 2017
    Encoder Based Lifelong LearningAmal Rannen, Rahaf Aljundi, Matthew B. Blaschko, Tinne TuytelaarsICCV · IMEC · KU Leuven
    PDF ↗
  10. 2018
    Lifelong Learning with Dynamically Expandable NetworksJaehong Yoon, Eunho Yang, Jeongtae Lee, Sung Ju HwangICLR · Korea Advanced Institute of Science and Technology
    PDF ↗
  11. 2017
    Habituation based synaptic plasticity and organismic learning in a quantum perovskiteFan Zuo, Priyadarshini Panda, Michele Kotiuga … Shriram RamanathanNature Communications · Purdue University West Lafayette · Rutgers, The State University of New Jersey · +3
    PDF ↗
  12. 2017
    Dual Track Multimodal Automatic Learning through Human-Robot InteractionShuqiang Jiang, Weiqing Min, Xue Li … Jiaqi ZhouIJCAI · Institute of Computing Technology · University of Chinese Academy of Sciences · +1
    PDF ↗
  13. 2017PDF ↗
  14. 2017PDF ↗
  15. 2017
    iCaRL: Incremental Classifier and Representation LearningSylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. LampertCVPR · Institute of Science and Technology Austria
    PDF ↗
  16. 2017
    Expert Gate: Lifelong Learning with a Network of ExpertsRahaf Aljundi, Punarjay Chakravarty, Tinne TuytelaarsCVPR · IMEC
    PDF ↗
  17. 2017
    Gradient Episodic Memory for Continual LearningDavid López-Paz, Marc’Aurelio RanzatoNeurIPS · Max Planck Society · Max Planck Innovation · +1
    PDF ↗
  18. 2017PDF ↗
  19. 2017
    Continual Learning with Deep Generative ReplayHanul Shin, Jung Kwon Lee, Jaehong Kim, Jiwon KimNeurIPS · Seoul National University · Samsung (South Korea)
    PDF ↗
  20. 2015
    The Extreme Value MachineEthan M. Rudd, Lalit P. Jain, Walter J. Scheirer, Terrance E. BoultTPAMI · University of Colorado Colorado Springs · University of Notre Dame
    PDF ↗
  21. 2017
    Continual Learning in Generative Adversarial NetsAri Seff, Alex Beatson, Daniel Suo, Han LiuarXiv · Princeton University
    PDF ↗
  22. 2017
    Streaming Sparse Gaussian Process ApproximationsThang D. Bui, Cuong V. Nguyen, Richard E. TurnerNeurIPS · University of Cambridge
    PDF ↗
  23. 2017PDF ↗
  24. 2017
    A Strategy for an Uncompromising Incremental LearnerRagav Venkatesan, Hemanth Venkateswara, Sethuraman Panchanathan, Baoxin LiarXiv
    PDF ↗
  25. 2017PDF ↗
  26. 2017
    Overcoming Catastrophic Forgetting by Incremental Moment MatchingSang-Woo Lee, Jin-Hwa Kim, Jae-Hyun Jun … Byoung‐Tak ZhangNeurIPS · Seoul National University · Naver (South Korea)
    PDF ↗
  27. 2017
    Overcoming catastrophic forgetting in neural networksJames Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz … Raia HadsellPNAS · Google DeepMind (United Kingdom) · Imperial College London
    PDF ↗
  28. 2017
    Improved multitask learning through synaptic intelligenceFriedemann Zenke, Ben Poole, Surya GanguliarXiv · Stanford University
    PDF ↗
  29. 2017
    Generative and Discriminative Text Classification with Recurrent Neural NetworksDani Yogatama, Chris Dyer, Ling Wang, Phil BlunsomarXiv · Baidu (China) · Carnegie Mellon University · +1
    PDF ↗
  30. 2017
    Meta NetworksTsendsuren Munkhdalai, Hong YuICML
    PDF ↗
  31. 2017
    A Deep Hierarchical Approach to Lifelong Learning in MinecraftChen Tessler, Shahar Givony, Tom Zahavy … Shie MannorAAAI · Technion – Israel Institute of Technology
    PDF ↗
  32. 2017
    PathNet: Evolution Channels Gradient Descent in Super Neural NetworksChrisantha Fernando, Dylan Banarse, Charles Blundell … Daan WierstraarXiv
    PDF ↗
  33. 2017
    Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing WorldSahil Garg, Irina Rish, Guillermo Cecchi, Aurélie LozanoIJCAI
    PDF ↗
  34. 2017
    A Joint Many-Task Model: Growing a Neural Network for Multiple NLP TasksKazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka, Richard SocherEMNLP · Salesforce (United States) · The University of Tokyo
    PDF ↗
  35. 2017
    Lifelong Learning CRF for Supervised Aspect ExtractionLei Shu, Hu Xu, Bing LiuACL · University of Illinois Chicago
    PDF ↗
  36. 2016
    A Fast, Robust, and Incremental Model for Learning High-Level Concepts From Human Motions by ImitationMina Alibeigi, Majid Nili Ahmadabadi, Babak Nadjar AraabiIEEE Transactions · University of Tehran · Institute for Research in Fundamental Sciences
    PDF ↗
  37. 2017
    Differentiable Programs with Neural LibrariesAlexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel TarlowICML · Microsoft (United States)
    PDF ↗
  38. 2016
    A Growing Long-term Episodic & Semantic MemoryMarc Pickett, Rami Al‐Rfou, Louis Shao, Chris TararXiv
    PDF ↗
  39. 2019
    A Reinforcement Learning Architecture That Transfers Knowledge Between Skills When Solving Multiple TasksPaolo Tommasino, Daniele Caligiore, Marco Mirolli, Gianluca BaldassarreIEEE TCDS · Nanyang Technological University · Institute of Cognitive Sciences and Technologies
    PDF ↗
  40. 2016
    Incremental One-Class Models for Data ClassificationTakoua Kefi, Riadh Ksantini, Mohamed Kaâniche, Adel BouhoulaarXiv
    PDF ↗
  41. 2016
    A novel progressive multi-label classifier for class-incremental dataMihika Dave, Sahil Tapiawala, Meng Joo Er, Rajasekar VenkatesanIEEE International Conference on Systems, Man and Cyberne… · Birla Institute of Technology and Science, Pilani · Nanyang Technological University
    PDF ↗
  42. 2016PDF ↗
  43. 2016
    Less-forgetting Learning in Deep Neural NetworksHeechul Jung, Jeongwoo Ju, Minju Jung, Junmo KimarXiv
    PDF ↗
  44. 2016
    Progressive Neural NetworksAndrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins … Raia HadsellarXiv
    PDF ↗
  45. 2016
    Active Long Term Memory NetworksTommaso Furlanello, Jiaping Zhao, Andrew Saxe … Bosco S. TjanarXiv
    PDF ↗
  46. 2016
    One-shot Learning with Memory-Augmented Neural NetworksAdam Santoro, Sergey Bartunov, Matthew Botvinick … Timothy LillicraparXiv
    PDF ↗
  47. 2016
    Incremental Object Recognition in Robotics with Extension to New Classes in Constant TimeR. Camoriano, Giulia Pasquale, C. Ciliberto … G. MettaarXiv
    PDF ↗
  48. 2016
    Online Open World RecognitionRocco De Rosa, Thomas Mensink, Barbara CaputoarXiv
    PDF ↗
  49. 2016
    Learning without ForgettingAuthors pendingECCV
    PDF ↗
  50. 2016PDF ↗
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.