# ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2306.03693 · HTML: https://mlsanity.com/paper/2306.03693/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 6 Jun 2023.

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

- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks](https://mlsanity.com/paper/2105.11654/) (2021)
- [Supervised learning based on temporal coding in spiking neural networks](https://mlsanity.com/paper/1606.08165/) (2016)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [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)
- [An Analytical Estimation of Spiking Neural Networks Energy Efficiency](https://mlsanity.com/paper/2210.13107/) (2022)
- [Network Plasticity as Bayesian Inference](https://mlsanity.com/paper/1504.05143/) (2015)
- [Connection Pruning for Deep Spiking Neural Networks with On-Chip Learning](https://mlsanity.com/paper/2010.04351/) (2020)

## Built on by (most cited first, 23 of 23)

- [Membrane Potential Batch Normalization for Spiking Neural Networks](https://mlsanity.com/paper/2308.08359/) (2023)
- [Spiking PointNet: Spiking Neural Networks for Point Clouds](https://mlsanity.com/paper/2310.06232/) (2023)
- [RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks](https://mlsanity.com/paper/2308.06787/) (2023)
- [Learning Long Sequences in Spiking Neural Networks](https://mlsanity.com/paper/2401.00955/) (2023)
- [Quantized Spike-driven Transformer](https://mlsanity.com/paper/2501.13492/) (2025)
- [Q-SNNs: Quantized Spiking Neural Networks](https://mlsanity.com/paper/2406.13672/) (2024)
- [Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN](https://mlsanity.com/paper/2403.03409/) (2024)
- [Enhancing Adversarial Robustness in SNNs with Sparse Gradients](https://mlsanity.com/paper/2405.20355/) (2024)
- [Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning](https://mlsanity.com/paper/2406.01072/) (2024)
- [PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining](https://mlsanity.com/paper/2505.05307/) (2025)
- [Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing](https://mlsanity.com/paper/2407.06452/) (2024)
- [Memory-Free and Parallel Computation for Quantized Spiking Neural Networks](https://mlsanity.com/paper/2503.00040/) (2025)
- [Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning](https://mlsanity.com/paper/2505.14535/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism](https://mlsanity.com/paper/2504.05621/) (2025)
- [Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks](https://mlsanity.com/paper/2504.20445/) (2025)
- [Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks](https://mlsanity.com/paper/2511.12097/) (2025)
- [Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams](https://mlsanity.com/paper/2401.10461/) (2024)
- [Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression](https://mlsanity.com/paper/2407.08744/) (2024)
- [Gated Parametric Neuron for Spike-based Audio Recognition](https://mlsanity.com/paper/2412.01087/) (2024)
- [NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration](https://mlsanity.com/paper/2508.21566/) (2025)
- [NeuRehab: A Reinforcement Learning and Spiking Neural Network-Based Rehab Automation Framework](https://mlsanity.com/paper/2512.17841/) (2025)
- [From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet](https://mlsanity.com/paper/2602.09717/) (2026)

## Abstract (arXiv)

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models further, the pruning methods have been explored to find sparse SNNs without redundancy connections after training. However, parameter redundancy still hinders the efficiency of SNNs during training. In the human brain, the rewiring process of neural networks is highly dynamic, while synaptic connections maintain relatively sparse during brain development. Inspired by this, here we propose an efficient evolutionary structure learning (ESL) framework for SNNs, named ESL-SNNs, to implement the sparse SNN training from scratch. The pruning and regeneration of synaptic connections in SNNs evolve dynamically during learning, yet keep the structural sparsity at a certain level. As a result, the ESL-SNNs can search for optimal sparse connectivity by exploring all possible parameters across time. Our experiments show that the proposed ESL-SNNs framework is able to learn SNNs with sparse structures effectively while reducing the limited accuracy. The ESL-SNNs achieve merely 0.28% accuracy loss with 10% connection density on the DVS-Cifar10 dataset. Our work presents a brand-new approach for sparse training of SNNs from scratch with biologically plausible evolutionary mechanisms, closing the gap in the expressibility between sparse training and dense training. Hence, it has great potential for SNN lightweight training and inference with low power consumption and small memory usage.