mlsanityData to 7 Oct 2026

Adversarial Continual Learning

arXiv 2003.09553 ↗First posted 21 Mar 2020cs.LG cs.AI cs.CVcited by 140

Not on the map. Why?

Abstract (arXiv)

Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We show that shared features are significantly less prone to forgetting and propose a novel hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks. Our model combines architecture growth to prevent forgetting of task-specific skills and an experience replay approach to preserve shared skills. We demonstrate our hybrid approach is effective in avoiding forgetting and show it is superior to both architecture-based and memory-based approaches on class incrementally learning of a single dataset as well as a sequence of multiple datasets in image classification. Our code is available at urlhttps://github.com/facebookresearch/Adversarial-Continual-Learning.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 26; 2023: 35; 2024: 29; 2025: 15; 2026: 13.

140 papers.

Sort:

By area:

  1. 2021Learning to Prompt for Continual Learningcited by 938
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  3. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  4. 2022Continual Test-Time Domain Adaptationcited by 520
  5. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
  6. 2021Gradient Projection Memory for Continual Learningcited by 338
  7. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  8. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  9. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 130
  10. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  11. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  12. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
38 more
  1. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 66
  2. 2025SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learningcited by 60
  3. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  4. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  5. 2022A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learningcited by 54
  6. 2023Better Generative Replay for Continual Federated Learningcited by 53
  7. 2022PIVOT: Prompting for Video Continual Learningcited by 45
  8. 2022Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interferencecited by 44
  9. 2024Mixture of Experts Meets Prompt-Based Continual Learningcited by 43
  10. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  11. 2023The Tunnel Effect: Building Data Representations in Deep Neural Networkscited by 34
  12. 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learningcited by 33
  13. 2021Continual Learning via Bit-Level Information Preservingcited by 32
  14. 2021Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffercited by 30
  15. 2024Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptationcited by 26
  16. 2021Multi-Domain Incremental Learning for Semantic Segmentationcited by 25
  17. 2021Optimizing Reusable Knowledge for Continual Learning via Metalearningcited by 24
  18. 2021Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representationscited by 24
  19. 2023Overcoming Generic Knowledge Loss with Selective Parameter Updatecited by 23
  20. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  21. 2024Adaptive Memory Replay for Continual Learningcited by 21
  22. 2023Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learningcited by 20
  23. 2023Multimodal Parameter-Efficient Few-Shot Class Incremental Learningcited by 19
  24. 2024Text-Enhanced Data-free Approach for Federated Class-Incremental Learningcited by 16
  25. 2023DualHSIC: HSIC-Bottleneck and Alignment for Continual Learningcited by 15
  26. 2023Learning to Prompt Knowledge Transfer for Open-World Continual Learningcited by 15
  27. 2021Saliency Guided Experience Packing for Replay in Continual Learningcited by 14
  28. 2022Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributionscited by 14
  29. 2021In Defense of the Learning Without Forgetting for Task Incremental Learningcited by 13
  30. 2023Overcoming the Stability Gap in Continual Learningcited by 13
  31. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  32. 2021Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgettingcited by 12
  33. 2021Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervisioncited by 12
  34. 2023Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memorycited by 12
  35. 2023Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modelingcited by 12
  36. 2023Continual Learning for Image Segmentation with Dynamic Querycited by 12
  37. 2024Continual Learning in the Frequency Domaincited by 12
  38. 2022Learn the Time to Learn: Replay Scheduling in Continual Learningcited by 11

50 most cited of 140 All 140 (JSON)