mlsanityData to 7 Oct 2026

Progress & Compress: A scalable framework for continual learning

arXiv 1805.06370 ↗First posted 16 May 2018stat.ML cs.LGcited by 516

Not on the map. Why?

Abstract (arXiv)

We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.

Key facts. Cited by 516 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 98; 2022: 90; 2023: 102; 2024: 95; 2025: 71; 2026: 60.

516 papers.

Sort:

By area:

  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  3. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  4. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  5. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  6. 2023Class-Incremental Learning: A Surveycited by 209
  7. 2023Mitigating the Alignment Tax of RLHFcited by 181
  8. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  9. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  10. 2022Continual Learning and Private Unlearningcited by 124
  11. 2022Understanding and Preventing Capacity Loss in Reinforcement Learningcited by 124
  12. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 121
38 more
  1. 2021Lifelong Pretraining: Continually Adapting Language Models to Emerging Corporacited by 114
  2. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  3. 2023SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understandingcited by 111
  4. 2023A Definition of Continual Reinforcement Learningcited by 98
  5. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  6. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  7. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 85
  8. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  9. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 80
  10. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 79
  11. 2022TRGP: Trust Region Gradient Projection for Continual Learningcited by 79
  12. 2022A Theoretical Study on Solving Continual Learningcited by 78
  13. 2023Model Merging by Uncertainty-Based Gradient Matchingcited by 77
  14. 2021AFEC: Active Forgetting of Negative Transfer in Continual Learningcited by 73
  15. 2024Continual Learning and Catastrophic Forgettingcited by 73
  16. 2022ELLE: Efficient Lifelong Pre-training for Emerging Datacited by 70
  17. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  18. 2021Continual Learning via Local Module Compositioncited by 61
  19. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  20. 2022Don't Stop Learning: Towards Continual Learning for the CLIP Modelcited by 61
  21. 2024CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Modelcited by 60
  22. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  23. 2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Modelscited by 54
  24. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  25. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  26. 2021Powerpropagation: A sparsity inducing weight reparameterisationcited by 49
  27. 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learningcited by 49
  28. 2021Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mappingcited by 47
  29. 2021Natural continual learning: success is a journey, not (just) a destinationcited by 46
  30. 2021Posterior Meta-Replay for Continual Learningcited by 45
  31. 2022Transfer without Forgettingcited by 44
  32. 2022Memory Efficient Continual Learning with Transformerscited by 43
  33. 2022CoSCL: Cooperation of Small Continual Learners is Stronger than a Big Onecited by 43
  34. 2023Improving Language Plasticity via Pretraining with Active Forgettingcited by 43
  35. 2023Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligencecited by 43
  36. 2021Same State, Different Task: Continual Reinforcement Learning without Interferencecited by 42
  37. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learningcited by 42
  38. 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41

50 most cited of 516 All 516 (JSON)