mlsanityData to 7 Oct 2026

Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay

arXiv 1903.04566 ↗First posted 11 Mar 2019cs.LG stat.MLcited by 51

Not on the map. Why?

Abstract (arXiv)

Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address this challenge by learning a generative model that couples the current task to the past learned tasks through a discriminative embedding space. We learn an abstract level generative distribution in the embedding that allows the generation of data points to represent the experience. We sample from this distribution and utilize experience replay to avoid forgetting and simultaneously accumulate new knowledge to the abstract distribution in order to couple the current task with past experience. We demonstrate theoretically and empirically that our framework learns a distribution in the embedding that is shared across all task and as a result tackles catastrophic forgetting.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 7; 2023: 11; 2024: 14; 2025: 7; 2026: 1.

51 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 110
  5. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  6. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 80
  7. 2022A Theoretical Study on Solving Continual Learningcited by 78
  8. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  9. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  10. 2021Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Taskscited by 46
  11. 2021Detection and Continual Learning of Novel Face Presentation Attackscited by 33
  12. 2021CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Taskscited by 29
38 more
  1. 2023Learnability and Algorithm for Continual Learningcited by 28
  2. 2022A Multi-Head Model for Continual Learning via Out-of-Distribution Replaycited by 27
  3. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  4. 2022Continual Learning Based on OOD Detection and Task Maskingcited by 21
  5. 2021Class-Incremental Experience Replay for Continual Learning under Concept Driftcited by 17
  6. 2021Cognitively Inspired Learning of Incremental Drifting Conceptscited by 16
  7. 2022Label-Efficient Online Continual Object Detection in Streaming Videocited by 16
  8. 2021Lifelong Learning with Sketched Structural Regularizationcited by 15
  9. 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspectivecited by 14
  10. 2021Continual Learning with Knowledge Transfer for Sentiment Classificationcited by 12
  11. 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypescited by 11
  12. 2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
  13. 2022TAME: Task Agnostic Continual Learning using Multiple Expertscited by 7
  14. 2023Sub-network Discovery and Soft-masking for Continual Learning of Mixed Taskscited by 7
  15. 2024Joint Diffusion models in Continual Learningcited by 6
  16. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  17. 2024GUIDE: Guidance-based Incremental Learning with Diffusion Modelscited by 5
  18. 2024UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completioncited by 5
  19. 2021Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separationcited by 4
  20. 2023Adiabatic replay for continual learningcited by 3
  21. 2024Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)cited by 3
  22. 2025Reliability-Adjusted Prioritized Experience Replaycited by 3
  23. 2022BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search enginescited by 2
  24. 2023Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representationcited by 2
  25. 2024HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learningcited by 2
  26. 2026On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Modelscited by 2
  27. 2023Condensed Prototype Replay for Class Incremental Learningcited by 1
  28. 2024Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replaycited by 1
  29. 2024Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Imagescited by 1
  30. 2024Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learningcited by 1
  31. 2025Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentationscited by 1
  32. 2023Robust Internal Representations for Domain Generalizationcited by 0
  33. 2023Adapt & Align: Continual Learning with Generative Models Latent Space Alignmentcited by 0
  34. 2024Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representationscited by 0
  35. 2024Unsupervised Federated Domain Adaptation for Segmentation of MRI Imagescited by 0
  36. 2024LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updatingcited by 0
  37. 2025Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classificationcited by 0
  38. 2025Towards Improving Long-Tail Entity Predictions in Temporal Knowledge Graphs through Global Similarity and Weighted Samplingcited by 0

50 most cited of 51 All 51 (JSON)