# Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2511.12097 · HTML: https://mlsanity.com/paper/2511.12097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Accelerating Sparse Deep Neural Networks](https://mlsanity.com/paper/2104.08378/) (2021)
- [Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch](https://mlsanity.com/paper/2102.04010/) (2021)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models](https://mlsanity.com/paper/2409.17481/) (2024)
- [Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN](https://mlsanity.com/paper/2305.19868/) (2023)
- [Pruning of Deep Spiking Neural Networks through Gradient Rewiring](https://mlsanity.com/paper/2105.04916/) (2021)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition](https://mlsanity.com/paper/2302.01172/) (2023)
- [ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks](https://mlsanity.com/paper/2306.03693/) (2023)
- [High-performance deep spiking neural networks with 0.3 spikes per neuron](https://mlsanity.com/paper/2306.08744/) (2023)
- [Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learning](https://mlsanity.com/paper/2312.17582/) (2023)
- [Constrained Submodular Maximization via New Bounds for DR-Submodular Functions](https://mlsanity.com/paper/2311.01129/) (2023)
- [Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning](https://mlsanity.com/paper/2406.01072/) (2024)
- [Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency](https://mlsanity.com/paper/2502.13572/) (2025)
- [Cross Knowledge Distillation between Artificial and Spiking Neural Networks](https://mlsanity.com/paper/2507.09269/) (2025)

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

- [Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2602.03284/) (2026)

## Abstract (arXiv)

Brain-inspired Spiking neural networks (SNNs) promise energy-efficient intelligence via event-driven, sparse computation, but deeper architectures inflate parameters and computational cost, hindering their edge deployment. Recent progress in SNN pruning helps alleviate this burden, yet existing efforts fall into only two families: unstructured pruning, which attains high sparsity but is difficult to accelerate on general hardware, and structured pruning, which eases deployment but lack flexibility and often degrades accuracy at matched sparsity. In this work, we introduce SpikeNM, the first SNN-oriented semi-structured (N:M) pruning framework that learns sparse SNNs from scratch, enforcing at most (N) non-zeros per (M)-weight block. To avoid the combinatorial space complexity (sumk=1NbinomMk) growing exponentially with (M), SpikeNM adopts an (M)-way basis-logit parameterization with a differentiable top-(k) sampler, linearizing per-block complexity to (mathcal O(M)) and enabling more aggressive sparsification. Further inspired by neuroscience, we propose eligibility-inspired distillation (EID), which converts temporally accumulated credits into block-wise soft targets to align mask probabilities with spiking dynamics, reducing sampling variance and stabilizing search under high sparsity. Experiments show that at (2:4) sparsity, SpikeNM maintains and even with gains across main-stream datasets, while yielding hardware-amenable patterns that complement intrinsic spike sparsity.