# LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks

arXiv: https://arxiv.org/abs/2503.21846 · HTML: https://mlsanity.com/paper/2503.21846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/1901.02985/) (2019)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Long short-term memory and learning-to-learn in networks of spiking neurons](https://mlsanity.com/paper/1803.09574/) (2018)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [DetNAS: Backbone Search for Object Detection](https://mlsanity.com/paper/1903.10979/) (2019)
- [GLiT: Neural Architecture Search for Global and Local Image Transformer](https://mlsanity.com/paper/2107.02960/) (2021)
- [Neural Architecture Search for Spiking Neural Networks](https://mlsanity.com/paper/2201.10355/) (2022)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/2003.11883/) (2020)
- [Training-free Transformer Architecture Search](https://mlsanity.com/paper/2203.12217/) (2022)
- [Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection](https://mlsanity.com/paper/2003.11818/) (2020)
- [BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2106.14033/) (2021)
- [Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives](https://mlsanity.com/paper/2409.08290/) (2024)
- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [Sparsity-aware generalization theory for deep neural networks](https://mlsanity.com/paper/2307.00426/) (2023)
- [Brain-inspired Evolutionary Architectures for Spiking Neural Networks](https://mlsanity.com/paper/2309.05263/) (2023)

## Built on by (most cited first, 1 of 1)

- [Line-based Event Preprocessing: Towards Low-Energy Neuromorphic Computer Vision](https://mlsanity.com/paper/2601.10742/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. However, most current SNN methods adopt architectures resembling traditional artificial neural networks (ANNs), leading to suboptimal performance when applied to SNNs. While SNNs excel in energy efficiency, they have been associated with lower accuracy levels than traditional ANNs when utilizing conventional architectures. In response, in this work we present LightSNN, a rapid and efficient Neural Network Architecture Search (NAS) technique specifically tailored for SNNs that autonomously leverages the most suitable architecture, striking a good balance between accuracy and efficiency by enforcing sparsity. Based on the spiking NAS network (SNASNet) framework, a cell-based search space including backward connections is utilized to build our training-free pruning-based NAS mechanism. Our technique assesses diverse spike activation patterns across different data samples using a sparsity-aware Hamming distance fitness evaluation. Thorough experiments are conducted on both static (CIFAR10 and CIFAR100) and neuromorphic datasets (DVS128-Gesture). Our LightSNN model achieves state-of-the-art results on CIFAR10 and CIFAR100, improves performance on DVS128Gesture by 4.49%, and significantly reduces search time most notably offering a 98× speedup over SNASNet and running 30% faster than the best existing method on DVS128Gesture. Code is available on Github at: https://github.com/YesmineAbdennadher/LightSNN.