# ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference

arXiv: https://arxiv.org/abs/2508.01223 · HTML: https://mlsanity.com/paper/2508.01223/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [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)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [SEENN: Towards Temporal Spiking Early-Exit Neural Networks](https://mlsanity.com/paper/2304.01230/) (2023)
- [Momentum Residual Neural Networks](https://mlsanity.com/paper/2102.07870/) (2021)
- [Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks](https://mlsanity.com/paper/1908.06378/) (2019)
- [A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation](https://mlsanity.com/paper/1906.06148/) (2019)
- [Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence](https://mlsanity.com/paper/2303.10276/) (2023)
- [High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference Cost](https://mlsanity.com/paper/2405.16466/) (2024)
- [A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception](https://mlsanity.com/paper/2303.14176/) (2023)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block](https://mlsanity.com/paper/2203.10006/) (2022)
- [Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning](https://mlsanity.com/paper/2401.04105/) (2024)

## Abstract (arXiv)

Reversible Spiking Neural Networks (RevSNNs) enable memory-efficient training by reconstructing forward activations during backpropagation, but suffer from high latency due to strictly sequential computation. To overcome this limitation, we propose ParaRevSNN, a parallel reversible SNN architecture that decouples sequential dependencies between reversible blocks while preserving reversibility. This design enables inter-block parallelism, significantly accelerating training and inference while retaining the memory-saving benefits of reversibility. Experiments on CIFAR10, CIFAR100, CIFAR10-DVS, and DVS128 Gesture demonstrate that ParaRevSNN matches or exceeds the accuracy of standard RevSNNs, while reducing training time by up to 35.2% and inference time to 18.15%, making it well-suited for deployment in resource-constrained scenarios.