# Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control

arXiv: https://arxiv.org/abs/1907.13322 · HTML: https://mlsanity.com/paper/1907.13322/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2019.

## Built on by (most cited first, 30 of 36)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Don't Stop Learning: Towards Continual Learning for the CLIP Model](https://mlsanity.com/paper/2207.09248/) (2022)
- [CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering](https://mlsanity.com/paper/2503.00413/) (2025)
- [Meta-attention for ViT-backed Continual Learning](https://mlsanity.com/paper/2203.11684/) (2022)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach](https://mlsanity.com/paper/2106.14563/) (2021)
- [Continual Learning via Inter-Task Synaptic Mapping](https://mlsanity.com/paper/2106.13954/) (2021)
- [Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting](https://mlsanity.com/paper/2410.00771/) (2024)
- [CNLL: A Semi-supervised Approach For Continual Noisy Label Learning](https://mlsanity.com/paper/2204.09881/) (2022)
- [DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics](https://mlsanity.com/paper/2403.14353/) (2024)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [Assessor-Guided Learning for Continual Environments](https://mlsanity.com/paper/2303.11624/) (2023)
- [Scalable Adversarial Online Continual Learning](https://mlsanity.com/paper/2209.01558/) (2022)
- [Dynamic Object Queries for Transformer-based Incremental Object Detection](https://mlsanity.com/paper/2407.21687/) (2024)
- [Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning](https://mlsanity.com/paper/2311.01227/) (2023)
- [Few-Shot Continual Learning via Flat-to-Wide Approaches](https://mlsanity.com/paper/2306.14369/) (2023)
- [Few-Shot Class Incremental Learning via Robust Transformer Approach](https://mlsanity.com/paper/2405.05984/) (2024)
- [Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond](https://mlsanity.com/paper/2408.02983/) (2024)
- [IF2Net: Innately Forgetting-Free Networks for Continual Learning](https://mlsanity.com/paper/2306.10480/) (2023)
- [Continual Knowledge Consolidation LORA for Domain Incremental Learning](https://mlsanity.com/paper/2510.16077/) (2025)
- [Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion](https://mlsanity.com/paper/2312.07082/) (2023)
- [Cross-Domain Continual Learning via CLAMP](https://mlsanity.com/paper/2405.07142/) (2024)
- [Forward-Backward Knowledge Distillation for Continual Clustering](https://mlsanity.com/paper/2405.19234/) (2024)
- [Decision Boundary-aware Knowledge Consolidation Generates Better Instance-Incremental Learner](https://mlsanity.com/paper/2406.03065/) (2024)
- [Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2406.18574/) (2024)
- [Sketch of a novel approach to a neural model](https://mlsanity.com/paper/2209.06865/) (2022)
- [One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning](https://mlsanity.com/paper/2407.09011/) (2024)
- [Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning](https://mlsanity.com/paper/2504.08000/) (2025)

## Abstract (arXiv)

To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning a new task, the proposed method preserves the knowledge for the previous tasks by controlling the plasticity of the network at the neuron level. NPC estimates the importance value of each neuron and consolidates important textitneurons by applying lower learning rates, rather than restricting individual connection weights to stay close to certain values. The experimental results on the incremental MNIST (iMNIST) and incremental CIFAR100 (iCIFAR100) datasets show that neuron-level consolidation is substantially more effective compared to the connection-level consolidation approaches.