# Preserving Plasticity in Continual Learning with Adaptive Linearity Injection

arXiv: https://arxiv.org/abs/2505.09486 · HTML: https://mlsanity.com/paper/2505.09486/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 16 of 16)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [The Dormant Neuron Phenomenon in Deep Reinforcement Learning](https://mlsanity.com/paper/2302.12902/) (2023)
- [Understanding plasticity in neural networks](https://mlsanity.com/paper/2303.01486/) (2023)
- [Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2010.14498/) (2020)
- [Loss of Plasticity in Continual Deep Reinforcement Learning](https://mlsanity.com/paper/2303.07507/) (2023)
- [A survey on modern trainable activation functions](https://mlsanity.com/paper/2005.00817/) (2020)
- [Disentangling the Causes of Plasticity Loss in Neural Networks](https://mlsanity.com/paper/2402.18762/) (2024)
- [Deep Reinforcement Learning with Plasticity Injection](https://mlsanity.com/paper/2305.15555/) (2023)
- [Maintaining Plasticity in Continual Learning via Regenerative Regularization](https://mlsanity.com/paper/2308.11958/) (2023)
- [Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks](https://mlsanity.com/paper/2406.02596/) (2024)
- [Parametric Exponential Linear Unit for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1605.09332/) (2016)
- [Parseval Regularization for Continual Reinforcement Learning](https://mlsanity.com/paper/2412.07224/) (2024)
- [Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset](https://mlsanity.com/paper/2411.04034/) (2024)
- [Plastic Learning with Deep Fourier Features](https://mlsanity.com/paper/2410.20634/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Unified Noise-Curvature View of Loss of Trainability](https://mlsanity.com/paper/2509.19698/) (2025)
- [NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning](https://mlsanity.com/paper/2608.04358/) (2026)

## Abstract (arXiv)

Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-stationary problem settings. Recent work has shown that deep linear networks tend to be resilient towards loss of plasticity. Motivated by this observation, we propose Adaptive Linearization (AdaLin), a general approach that dynamically adapts each neuron's activation function to mitigate plasticity loss. Unlike prior methods that rely on regularization or periodic resets, AdaLin equips every neuron with a learnable parameter and a gating mechanism that injects linearity into the activation function based on its gradient flow. This adaptive modulation ensures sufficient gradient signal and sustains continual learning without introducing additional hyperparameters or requiring explicit task boundaries. When used with conventional activation functions like ReLU, Tanh, and GeLU, we demonstrate that AdaLin can significantly improve performance on standard benchmarks, including Random Label and Permuted MNIST, Random Label and Shuffled CIFAR-10, and Class-Split CIFAR-100. Furthermore, its efficacy is shown in more complex scenarios, such as class-incremental learning on CIFAR-100 with a ResNet-18 backbone, and in mitigating plasticity loss in off-policy reinforcement learning agents. We perform a systematic set of ablations that show that neuron-level adaptation is crucial for good performance and analyze a number of metrics in the network that might be correlated to loss of plasticity.