# Adaptive Sparse Structure Development with Pruning and Regeneration for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2211.12219 · HTML: https://mlsanity.com/paper/2211.12219/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 47 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Deep Rewiring: Training very sparse deep networks](https://mlsanity.com/paper/1711.05136/) (2017)
- [STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition](https://mlsanity.com/paper/1710.04734/) (2017)
- [Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization](https://mlsanity.com/paper/1911.00822/) (2019)
- [Pruning of Deep Spiking Neural Networks through Gradient Rewiring](https://mlsanity.com/paper/2105.04916/) (2021)
- [BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation](https://mlsanity.com/paper/2207.08533/) (2022)
- [Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines](https://mlsanity.com/paper/1511.04484/) (2015)
- [Energy-efficient Knowledge Distillation for Spiking Neural Networks](https://mlsanity.com/paper/2106.07172/) (2021)
- [Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection](https://mlsanity.com/paper/1910.09993/) (2019)
- [Connection Pruning for Deep Spiking Neural Networks with On-Chip Learning](https://mlsanity.com/paper/2010.04351/) (2020)

## Built on by (most cited first, 9 of 9)

- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks](https://mlsanity.com/paper/2308.04749/) (2023)
- [Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning](https://mlsanity.com/paper/2406.01072/) (2024)
- [Sparse-firing regularization methods for spiking neural networks with time-to-first spike coding](https://mlsanity.com/paper/2307.13007/) (2023)
- [Communication Trade-offs in Federated Learning of Spiking Neural Networks](https://mlsanity.com/paper/2303.00928/) (2023)
- [Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism](https://mlsanity.com/paper/2504.05621/) (2025)
- [Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression](https://mlsanity.com/paper/2407.08744/) (2024)
- [Topology Optimization of Random Memristors for Input-Aware Dynamic SNN](https://mlsanity.com/paper/2407.18625/) (2024)
- [SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning](https://mlsanity.com/paper/2507.02945/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) are more biologically plausible and computationally efficient. Therefore, SNNs have the natural advantage of drawing the sparse structural plasticity of brain development to alleviate the energy problems of deep neural networks caused by their complex and fixed structures. However, previous SNNs compression works are lack of in-depth inspiration from the brain development plasticity mechanism. This paper proposed a novel method for the adaptive structural development of SNN (SD-SNN), introducing dendritic spine plasticity-based synaptic constraint, neuronal pruning and synaptic regeneration. We found that synaptic constraint and neuronal pruning can detect and remove a large amount of redundancy in SNNs, coupled with synaptic regeneration can effectively prevent and repair over-pruning. Moreover, inspired by the neurotrophic hypothesis, neuronal pruning rate and synaptic regeneration rate were adaptively adjusted during the learning-while-pruning process, which eventually led to the structural stability of SNNs. Experimental results on spatial (MNIST, CIFAR-10) and temporal neuromorphic (N-MNIST, DVS-Gesture) datasets demonstrate that our method can flexibly learn appropriate compression rate for various tasks and effectively achieve superior performance while massively reducing the network energy consumption. Specifically, for the spatial MNIST dataset, our SD-SNN achieves 99.51% accuracy at the pruning rate 49.83%, which has a 0.05% accuracy improvement compared to the baseline without compression. For the neuromorphic DVS-Gesture dataset, 98.20% accuracy with 1.09% improvement is achieved by our method when the compression rate reaches 55.50%.