# Spiking Brain Compression: Post-Training Second-order Compression for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2506.03996 · HTML: https://mlsanity.com/paper/2506.03996/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Layer-adaptive sparsity for the Magnitude-based Pruning](https://mlsanity.com/paper/2010.07611/) (2020)
- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2102.04487/) (2021)
- [Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization](https://mlsanity.com/paper/1911.00822/) (2019)
- [Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation](https://mlsanity.com/paper/2304.05627/) (2023)
- [The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticity](https://mlsanity.com/paper/2201.11063/) (2022)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket](https://mlsanity.com/paper/2401.02020/) (2024)
- [Distilling Spikes: Knowledge Distillation in Spiking Neural Networks](https://mlsanity.com/paper/2005.00288/) (2020)
- [Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions](https://mlsanity.com/paper/2203.07006/) (2022)
- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks](https://mlsanity.com/paper/2104.12528/) (2021)
- [QP-SNN: Quantized and Pruned Spiking Neural Networks](https://mlsanity.com/paper/2502.05905/) (2025)
- [Hessian Aware Quantization of Spiking Neural Networks](https://mlsanity.com/paper/2104.14117/) (2021)
- [Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function](https://mlsanity.com/paper/2305.19295/) (2023)
- [SpikeExplorer: hardware-oriented Design Space Exploration for Spiking Neural Networks on FPGA](https://mlsanity.com/paper/2404.03714/) (2024)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have emerged as a new generation of energy-efficient neural networks suitable for implementation on neuromorphic hardware. As neuromorphic hardware has limited memory and computational resources, parameter pruning and quantization have recently been explored to improve the efficiency of SNNs. State-of-the-art SNN pruning/quantization methods employ multiple compression and training iterations, increasing the cost for pre-trained or very large SNNs. In this paper, we propose a novel one-shot post-training compression framework, Spiking Brain Compression (SBC), that extends the classical Optimal Brain Surgeon method to SNNs. SBC replaces the current-based objective found in the common layer-wise compression method with a spike-train-based objective whose Hessian is cheaply computable, allowing a single backward pass to compress parameters and analytically rescale the rest. Applying SBC to SNN pruning and quantization across event-based and static datasets (up to ImageNet), including SEW-ResNet152 and spike-driven Transformers, we achieve state-of-the-art one-shot post-training compression for SNNs, with single- to double-digit accuracy gains over ANN compression baselines ported to SNNs. We further report a synaptic-operation-based energy proxy and a calibration-size ablation, demonstrating robust performance under sub-one-sample-per-class calibration.