# Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency

arXiv: https://arxiv.org/abs/2305.14174 · HTML: https://mlsanity.com/paper/2305.14174/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2023.

## Built on by (most cited first, 10 of 10)

- [TIM: An Efficient Temporal Interaction Module for Spiking Transformer](https://mlsanity.com/paper/2401.11687/) (2024)
- [Cross Knowledge Distillation between Artificial and Spiking Neural Networks](https://mlsanity.com/paper/2507.09269/) (2025)
- [Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain](https://mlsanity.com/paper/2511.12150/) (2025)
- [Brain-inspired and Self-based Artificial Intelligence](https://mlsanity.com/paper/2402.18784/) (2024)
- [Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble](https://mlsanity.com/paper/2508.11279/) (2025)
- [A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2606.11236/) (2026)
- [Accuracy-Efficiency Trade-Offs in Spiking Neural Networks: A Lempel-Ziv Complexity Perspective on Learning Rules](https://mlsanity.com/paper/2506.06750/) (2025)
- [Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain](https://mlsanity.com/paper/2509.12959/) (2025)
- [SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks](https://mlsanity.com/paper/2509.22581/) (2025)
- [Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks](https://mlsanity.com/paper/2605.14252/) (2026)

## Abstract (arXiv)

Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to impressive performance in various tasks. However, spiking neural networks trained with backpropagation typically approximate actual labels using the average output, often necessitating a larger simulation timestep to enhance the network's performance. This delay constraint poses a challenge to the further advancement of SNNs. Current training algorithms tend to overlook the differences in output distribution at various timesteps. Particularly for neuromorphic datasets, inputs at different timesteps can cause inconsistencies in output distribution, leading to a significant deviation from the optimal direction when combining optimization directions from different moments. To tackle this issue, we have designed a method to enhance the temporal consistency of outputs at different timesteps. We have conducted experiments on static datasets such as CIFAR10, CIFAR100, and ImageNet. The results demonstrate that our algorithm can achieve comparable performance to other optimal SNN algorithms. Notably, our algorithm has achieved state-of-the-art performance on neuromorphic datasets DVS-CIFAR10 and N-Caltech101, and can achieve superior performance in the test phase with timestep T=1.