Related work

The foundational work on continual learning, 1988 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

958 papers of 6,984 · showing 701–750Sort Recent · Most cited
  1. 2023
    Theory on Forgetting and Generalization of Continual LearningSen Lin, Peizhong Ju, Yingbin Liang, Ness B. ShroffICML
    PDF ↗
  2. 2023PDF ↗
  3. 2023
    Adaptive model training strategy for continuous classification of time seriesChenxi Sun, Hongyan Li, Moxian Song … linda QiaoApplied Intelligence
  4. 2023
    Federated probability memory recall for federated continual learningZhe Wang, Yu Zhang, Xinlei Xu … Wenli DuInformation Sciences · East China University of Science and Technology
  5. 2023
    Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech RecognitionLeyuan Qu, Cornelius Weber, Stefan WermterNeural Networks · Universität Hamburg · Zhejiang Lab · +2
    PDF ↗
  6. 2023
    Improving transparency and representational generalizability through parallel continual learningM Paknezhad, Hamsawardhini Rengarajan, Chenghao Yuan … Hwee Kuan LeeNeural Networks · Agency for Science, Technology and Research · Bioinformatics Institute · +2
  7. 2023
    Continual Pre-training of Language ModelsZixuan Ke, Yijia Shao, Haowei Lin … Bing LiuICLR
    PDF ↗
  8. 2023
    Exploring the Benefits of Training Expert Language Models over Instruction TuningJoel Jang, Seungone Kim, Seonghyeon Ye … Minjoon SeoICML
    PDF ↗
  9. 2023PDF ↗
  10. 2023
    Efficient Parametric Approximations of Neural Network Function Space DistanceNikita Dhawan, Sicong Huang, Juhan Bae, Roger GrosseICML
    PDF ↗
  11. 2023PDF ↗
  12. 2023PDF ↗
  13. 2023
    Flexible few-shot class-incremental learning with prototype containerXinlei Xu, Zhe Wang, Zhiling Fu … Dongdong LiNeural Computing and Applications · East China University of Science and Technology
  14. 2023
    SuperFormer: Continual learning superposition method for text classificationMarko Zeman, Jana Faganeli Pucer, Igor Kononenko, Zoran BosnićNeural Networks · University of Ljubljana
    PDF ↗
  15. 2023
    SATS: Self-Attention Transfer for Continual Semantic SegmentationYiqiao Qiu, Yixing Shen, Zhuohao Sun … Ruixuan WangPattern Recognition · Sun Yat-sen University · Wuhan University · +2
    PDF ↗
  16. 2023
    Continual Image Deraining With Hypergraph Convolutional NetworksXueyang Fu, Jie Xiao, Yurui Zhu … Zheng-Jun ZhaTPAMI · University of Science and Technology of China
  17. 2023PDF ↗
  18. 2023
    Avalanche: A PyTorch Library for Deep Continual LearningAntonio Carta, Lorenzo Pellegrini, Andrea Cossu … Vincenzo LomonacoJMLR
    PDF ↗
  19. 2023
    Neuro Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept RehearsalEmanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra … Stefano TesoICML
    PDF ↗
  20. 2023PDF ↗
  21. 2023
    Continual Pedestrian Trajectory Learning With Social Generative ReplayYa Wu, Ariyan Bighashdel, G. Chen … P. JancuraRA-L
  22. 2023
    Towards Label-Efficient Incremental Learning: A SurveyMert Kilickaya, Joost van de Weijer, Yuki M. AsanoarXiv
    PDF ↗
  23. 2023
    Utilizing Priming to Identify Optimal Class Ordering to Alleviate Catastrophic ForgettingGabriel Mantione-Holmes, Justin Leo, Jugal KalitaIEEE 17th International Conference on Semantic Computing… · Lewis & Clark College · University of Colorado Boulder · +2
    PDF ↗
  24. 2023
    Progressive Prompts: Continual Learning for Language ModelsAnastasia Razdaibiedina, Yuning Mao, Rui Hou … Amjad AlmahairiICLR
    PDF ↗
  25. 2023
    Restricted Orthogonal Gradient Projection for Continual LearningZeyuan Yang, Zonghan Yang, Peng Li, Yang LiuAI Open
    PDF ↗
  26. 2023PDF ↗
  27. 2023PDF ↗
  28. 2023
    Class-Incremental Learning with RepetitionHamed Hemati, Andrea Cossu, Antonio Carta … Damian BorthCoLLAs
    PDF ↗
  29. 2023
    Graph Lifelong Learning: A SurveyFalih Gozi Febrinanto, Feng Xia, Kristen Moore … Charu C. AggarwalIEEE Computational Intelligence Magazine · Federation University · Commonwealth Scientific and Industrial Research Organisation · +1
    PDF ↗
  30. 2023
    DEJA VU: Continual Model Generalization For Unseen DomainsChenxi Liu, Lixu Wang, Lingjuan Lyu … Qi ZhuICLR
    PDF ↗
  31. 2023
    Leveraging joint incremental learning objective with data ensemble for class incremental learningPratik Mazumder, Mohammed Asad Karim, Indu Joshi, Pravendra SinghNeural Networks · Indian Institute of Technology Jodhpur · Carnegie Mellon University · +2
  32. 2023
    Multi-lingual agents through multi-headed neural networksJonathan D. Thomas, Ra ́ul Santos-Rodr ́ıguez, Mihai Anca, Robert J. PiechockiNorthern Lights Deep Learning Workshop · University of Bristol
    PDF ↗
  33. 2023PDF ↗
  34. 2023
    Continual task learning in natural and artificial agentsTimo Flesch, Andrew Saxe, Christopher SummerfieldTrends in Neurosciences · University of Oxford · Sainsbury Laboratory · +3
    PDF ↗
  35. 2023
    A Domain-Agnostic Approach for Characterization of Lifelong Learning SystemsMegan M. Baker, Alexander New, Mario Aguilar-Simon … Gautam K. VallabhaNeural Networks · Johns Hopkins University Applied Physics Laboratory · Teledyne Technologies (United States) · +13
    PDF ↗
  36. 2023
    Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signalsTimo Flesch, Dávid Nagy, Andrew Saxe, Christopher SummerfieldPLOS · University of Oxford · HUN-REN Wigner Research Centre for Physics · +5
    PDF ↗
  37. 2023
    Distilled Meta-learning for Multi-Class Incremental LearningHao Liu, Zhaoyu Yan, Bing Liu … Abdulmotaleb El SaddikACM Transactions · China University of Mining and Technology · University of Ottawa
    PDF ↗
  38. 2023
    Artificial Neuronal Ensembles with Learned Context Dependent GatingM. J. Tilley, Michelle Miller, David A. FreedmanICLR
    PDF ↗
  39. 2023
    Sim-Anchored Learning for On-the-Fly AdaptationBassel El Mabsout, Shahin Roozkhosh, Siddharth Mysore … Renato MancusoarXiv
    PDF ↗
  40. 2023PDF ↗
  41. 2023
    Self-recovery of memory via generative replayZhenglong Zhou, Geshi Yeung, Anna C. SchapiroarXiv
    PDF ↗
  42. 2023
    Continual prune-and-select: class-incremental learning with specialized subnetworksAleksandr Dekhovich, David M. J. Tax, Marcel H. F. Sluiter, Miguel A. BessaApplied Intelligence · Delft University of Technology · Brown University
    PDF ↗
  43. 2023
    On-device synaptic memory consolidation using Fowler-Nordheim quantum-tunnelingMustafizur Rahman, Subhankar Bose, Shantanu ChakrabarttyFrontiers · Washington University in St. Louis
    PDF ↗
  44. 2023PDF ↗
  45. 2023
    Knowledge aggregation networks for class incremental learningZhiling Fu, Zhe Wang, Xinlei Xu … Hai YangPattern Recognition · East China University of Science and Technology
  46. 2023
    A Distinct Unsupervised Reference Model From The Environment Helps Continual LearningSeyyed AmirHossein Ameli Kalkhoran, Mohammadamin Banayeeanzade, Mahdi Samiei, Mahdieh Soleymani BaghshaharXiv
    PDF ↗
  47. 2023
    Damage Control During Domain Adaptation for Transducer Based Automatic Speech RecognitionSomshubra Majumdar, Shantanu Acharya, Vitaly Lavrukhin, Boris GinsburgIEEE Spoken Language Technology Workshop (SLT)
    PDF ↗
  48. 2023
    On the challenges to learn from Natural Data StreamsGuido Borghi, Gabriele Graffieti, Davide MaltoniarXiv
    PDF ↗
  49. 2023
    Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual LearningVincenzo Lomonaco, Lorenzo Pellegrini, Gabriele Graffieti, Davide MaltoniarXiv
    PDF ↗
  50. 2023
    Generative appearance replay for continual unsupervised domain adaptationBoqi Chen, Kevin Thandiackal, Pushpak Pati, O. GokselMedical Image Anal.
    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. 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.