# Maintaining Plasticity in Deep Continual Learning

arXiv: https://arxiv.org/abs/2306.13812 · HTML: https://mlsanity.com/paper/2306.13812/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 98 references that are in the map.
- First posted on arXiv 23 Jun 2023.

## Builds on (most cited first, 30 of 53)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)

## Built on by (most cited first, 30 of 43)

- [Maintaining Plasticity in Continual Learning via Regenerative Regularization](https://mlsanity.com/paper/2308.11958/) (2023)
- [Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2404.00781/) (2024)
- [Hyperspherical Normalization for Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.15280/) (2025)
- [Learning Continually by Spectral Regularization](https://mlsanity.com/paper/2406.06811/) (2024)
- [Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages](https://mlsanity.com/paper/2310.07418/) (2023)
- [No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO](https://mlsanity.com/paper/2405.00662/) (2024)
- [Directions of Curvature as an Explanation for Loss of Plasticity](https://mlsanity.com/paper/2312.00246/) (2023)
- [A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning](https://mlsanity.com/paper/2405.19153/) (2024)
- [Symmetry Induces Structure and Constraint of Learning](https://mlsanity.com/paper/2309.16932/) (2023)
- [Plasticity Loss in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2411.04832/) (2024)
- [Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn](https://mlsanity.com/paper/2506.00592/) (2025)
- [Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play](https://mlsanity.com/paper/2411.00062/) (2024)
- [Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn](https://mlsanity.com/paper/2409.04792/) (2024)
- [Lightweight Online Adaption for Time Series Foundation Model Forecasts](https://mlsanity.com/paper/2502.12920/) (2025)
- [Self-Normalized Resets for Plasticity in Continual Learning](https://mlsanity.com/paper/2410.20098/) (2024)
- [Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models](https://mlsanity.com/paper/2606.14222/) (2026)
- [Remove Symmetries to Control Model Expressivity and Improve Optimization](https://mlsanity.com/paper/2408.15495/) (2024)
- [Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss](https://mlsanity.com/paper/2502.01342/) (2025)
- [Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs](https://mlsanity.com/paper/2503.07663/) (2025)
- [Reinitializing weights vs units for maintaining plasticity in neural networks](https://mlsanity.com/paper/2508.00212/) (2025)
- [The Need for a Big World Simulator: A Scientific Challenge for Continual Learning](https://mlsanity.com/paper/2408.02930/) (2024)
- [Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution](https://mlsanity.com/paper/2412.13492/) (2024)
- [Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity](https://mlsanity.com/paper/2510.00304/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective](https://mlsanity.com/paper/2605.09044/) (2026)
- [Continual Policy Consolidation for Lifelong Robot Learning](https://mlsanity.com/paper/2601.22475/) (2026)
- [Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion](https://mlsanity.com/paper/2408.09838/) (2024)
- [Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2508.06871/) (2025)
- [Convergent World Representations and Divergent Tasks](https://mlsanity.com/paper/2602.00533/) (2026)
- [Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization](https://mlsanity.com/paper/2309.08546/) (2023)

## Abstract (arXiv)

Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occurs continually. If deep-learning systems are applied in a continual learning setting, then it is well known that they may fail to remember earlier examples. More fundamental, but less well known, is that they may also lose their ability to learn on new examples, a phenomenon called loss of plasticity. We provide direct demonstrations of loss of plasticity using the MNIST and ImageNet datasets repurposed for continual learning as sequences of tasks. In ImageNet, binary classification performance dropped from 89% accuracy on an early task down to 77%, about the level of a linear network, on the 2000th task. Loss of plasticity occurred with a wide range of deep network architectures, optimizers, activation functions, batch normalization, dropout, but was substantially eased by L2-regularization, particularly when combined with weight perturbation. Further, we introduce a new algorithm -- continual backpropagation -- which slightly modifies conventional backpropagation to reinitialize a small fraction of less-used units after each example and appears to maintain plasticity indefinitely.