# Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay

arXiv: https://arxiv.org/abs/1903.04566 · HTML: https://mlsanity.com/paper/1903.04566/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

## Built on by (most cited first, 30 of 51)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System](https://mlsanity.com/paper/2201.12604/) (2022)
- [Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2112.02706/) (2021)
- [Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks](https://mlsanity.com/paper/2112.10017/) (2021)
- [A Theoretical Study on Solving Continual Learning](https://mlsanity.com/paper/2211.02633/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning](https://mlsanity.com/paper/2403.18886/) (2024)
- [Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.03271/) (2021)
- [Detection and Continual Learning of Novel Face Presentation Attacks](https://mlsanity.com/paper/2108.12081/) (2021)
- [CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.02714/) (2021)
- [Learnability and Algorithm for Continual Learning](https://mlsanity.com/paper/2306.12646/) (2023)
- [A Multi-Head Model for Continual Learning via Out-of-Distribution Replay](https://mlsanity.com/paper/2208.09734/) (2022)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Continual Learning Based on OOD Detection and Task Masking](https://mlsanity.com/paper/2203.09450/) (2022)
- [Class-Incremental Experience Replay for Continual Learning under Concept Drift](https://mlsanity.com/paper/2104.11861/) (2021)
- [Cognitively Inspired Learning of Incremental Drifting Concepts](https://mlsanity.com/paper/2110.04662/) (2021)
- [Label-Efficient Online Continual Object Detection in Streaming Video](https://mlsanity.com/paper/2206.00309/) (2022)
- [Lifelong Learning with Sketched Structural Regularization](https://mlsanity.com/paper/2104.08604/) (2021)
- [Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective](https://mlsanity.com/paper/2506.03951/) (2025)
- [Continual Learning with Knowledge Transfer for Sentiment Classification](https://mlsanity.com/paper/2112.10021/) (2021)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [TAME: Task Agnostic Continual Learning using Multiple Experts](https://mlsanity.com/paper/2210.03869/) (2022)
- [Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks](https://mlsanity.com/paper/2401.15275/) (2024)
- [Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks](https://mlsanity.com/paper/2310.09436/) (2023)
- [Joint Diffusion models in Continual Learning](https://mlsanity.com/paper/2411.08224/) (2024)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [GUIDE: Guidance-based Incremental Learning with Diffusion Models](https://mlsanity.com/paper/2403.03938/) (2024)
- [UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completion](https://mlsanity.com/paper/2410.18074/) (2024)

## 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.