{"ID":2887527,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01223","arxiv_id":"2508.01223","title":"ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference","abstract":"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.","short_abstract":"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 seque...","url_abs":"https://arxiv.org/abs/2508.01223","url_pdf":"https://arxiv.org/pdf/2508.01223v1","authors":"[\"Changqing Xu\",\"Guoqing Sun\",\"Yi Liu\",\"Xinfang Liao\",\"Yintang Yang\"]","published":"2025-08-02T06:40:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}