mlsanityData to 14 Oct 2026

Online Continual Learning with Maximally Interfered Retrieval

arXiv 1908.04742 ↗First posted 11 Aug 2019cs.LG stat.MLcited by 379

Not on the map. Why?

Abstract (arXiv)

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from the replay memory or from a generative model, which is suboptimal. In this work, we consider a controlled sampling of memories for replay. We retrieve the samples which are most interfered, i.e. whose prediction will be most negatively impacted by the foreseen parameters update. We show a formulation for this sampling criterion in both the generative replay and the experience replay setting, producing consistent gains in performance and greatly reduced forgetting. We release an implementation of our method at https://github.com/optimass/Maximally_Interfered_Retrieval.

Key facts. Cited by 379 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 55; 2022: 65; 2023: 83; 2024: 66; 2025: 52; 2026: 58.

379 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  3. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 271
  4. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  5. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 219
  6. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 198
  7. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  8. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  9. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 141
  10. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  11. 2024Simple and Scalable Strategies to Continually Pre-train Large Language Modelscited by 127
  12. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 124
38 more
  1. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 117
  2. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 116
  3. 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
  4. 2024Continual Learning and Catastrophic Forgettingcited by 77
  5. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  6. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
  7. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
  8. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 69
  9. 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 67
  10. 2023Lifelong Language Pretraining with Distribution-Specialized Expertscited by 66
  11. 2021Continual Learning via Local Module Compositioncited by 63
  12. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  13. 2023Computationally Budgeted Continual Learning: What Does Matter?cited by 61
  14. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  15. 2022Continual evaluation for lifelong learning: Identifying the stability gapcited by 56
  16. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  17. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  18. 2023Online Prototype Learning for Online Continual Learningcited by 53
  19. 2023PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learningcited by 52
  20. 2023Real-Time Evaluation in Online Continual Learning: A New Hopecited by 47
  21. 2021Posterior Meta-Replay for Continual Learningcited by 45
  22. 2022Learning Fast and Slow for Online Time Series Forecastingcited by 45
  23. 2022Exploring Example Influence in Continual Learningcited by 44
  24. 2021Same State, Different Task: Continual Reinforcement Learning without Interferencecited by 43
  25. 2023Maintaining Plasticity in Deep Continual Learningcited by 43
  26. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  27. 2022Continual Normalization: Rethinking Batch Normalization for Online Continual Learningcited by 40
  28. 2023Parameter-Level Soft-Masking for Continual Learningcited by 40
  29. 2021Class-Incremental Learning with Generative Classifierscited by 39
  30. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  31. 2022On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learningcited by 39
  32. 2024A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Datacited by 39
  33. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  34. 2021Understanding Continual Learning Settings with Data Distribution Drift Analysiscited by 38
  35. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  36. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  37. 2021Distilled Replay: Overcoming Forgetting through Synthetic Samplescited by 36
  38. 2022CLAD: A realistic Continual Learning benchmark for Autonomous Drivingcited by 36

50 most cited of 379 All 379 (JSON)