mlsanityData to 7 Oct 2026

Gradient based sample selection for online continual learning

arXiv 1903.08671 ↗First posted 20 Mar 2019cs.LG cs.AI cs.CVcited by 568

Not on the map. Why?

Abstract (arXiv)

A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal. Previous works often depend on task boundary and i.i.d. assumptions to properly select samples for the replay buffer. In this work, we formulate sample selection as a constraint reduction problem based on the constrained optimization view of continual learning. The goal is to select a fixed subset of constraints that best approximate the feasible region defined by the original constraints. We show that it is equivalent to maximizing the diversity of samples in the replay buffer with parameters gradient as the feature. We further develop a greedy alternative that is cheap and efficient. The advantage of the proposed method is demonstrated by comparing to other alternatives under the continual learning setting. Further comparisons are made against state of the art methods that rely on task boundaries which show comparable or even better results for our method.

Key facts. Cited by 568 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 73; 2022: 103; 2023: 135; 2024: 116; 2025: 81; 2026: 60.

568 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
  3. 2021Dataset Condensation with Distribution Matchingcited by 362
  4. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 290
  5. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  6. 2021Co2L: Contrastive Continual Learningcited by 243
  7. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  8. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  9. 2023Class-Incremental Learning: A Surveycited by 209
  10. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 189
  11. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  12. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
38 more
  1. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  2. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
  3. 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 146
  4. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
  5. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 139
  6. 2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 132
  7. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 130
  8. 2023Improved Distribution Matching for Dataset Condensationcited by 124
  9. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  10. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 115
  11. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
  12. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  13. 2022Efficient Dataset Distillation Using Random Feature Approximationcited by 111
  14. 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 110
  15. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  16. 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
  17. 2023DREAM: Efficient Dataset Distillation by Representative Matchingcited by 93
  18. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  19. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  20. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 79
  21. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  22. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  23. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  24. 2024Continual Learning and Catastrophic Forgettingcited by 73
  25. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  26. 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 66
  27. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  28. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  29. 2023Computationally Budgeted Continual Learning: What Does Matter?cited by 61
  30. 2022Graph Condensation via Receptive Field Distribution Matchingcited by 60
  31. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  32. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  33. 2022Continual evaluation for lifelong learning: Identifying the stability gapcited by 55
  34. 2022SparCL: Sparse Continual Learning on the Edgecited by 55
  35. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  36. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  37. 2023Online Prototype Learning for Online Continual Learningcited by 53
  38. 2023PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learningcited by 50

50 most cited of 568 All 568 (JSON)