# Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillation

arXiv: https://arxiv.org/abs/2511.12095 · HTML: https://mlsanity.com/paper/2511.12095/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Dataset Condensation with Distribution Matching](https://mlsanity.com/paper/2110.04181/) (2021)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Dataset Meta-Learning from Kernel Ridge-Regression](https://mlsanity.com/paper/2011.00050/) (2020)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Dataset Distillation using Neural Feature Regression](https://mlsanity.com/paper/2206.00719/) (2022)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Improved Distribution Matching for Dataset Condensation](https://mlsanity.com/paper/2307.09742/) (2023)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm](https://mlsanity.com/paper/2312.03526/) (2023)
- [M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy](https://mlsanity.com/paper/2312.15927/) (2023)
- [Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN](https://mlsanity.com/paper/2305.19868/) (2023)
- [Dataset Distillation with Neural Characteristic Function: A Minmax Perspective](https://mlsanity.com/paper/2502.20653/) (2025)
- [BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation](https://mlsanity.com/paper/2207.08533/) (2022)
- [Dataset Distillation by Automatic Training Trajectories](https://mlsanity.com/paper/2407.14245/) (2024)
- [Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods](https://mlsanity.com/paper/2405.04289/) (2024)
- [UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks](https://mlsanity.com/paper/2503.12905/) (2025)
- [Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity](https://mlsanity.com/paper/2506.12087/) (2025)
- [Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Time](https://mlsanity.com/paper/2201.07210/) (2021)

## Built on by (most cited first, 2 of 2)

- [Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2602.03284/) (2026)
- [ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compression](https://mlsanity.com/paper/2607.28020/) (2026)

## Abstract (arXiv)

Event cameras sense brightness changes and output binary asynchronous event streams, attracting increasing attention. Their bio-inspired dynamics align well with spiking neural networks (SNNs), offering a promising energy-efficient alternative to conventional vision systems. However, SNNs remain costly to train due to temporal coding, which limits their practical deployment. To alleviate the high training cost of SNNs, we introduce PACE (Phase-Aligned Condensation for Events), the first dataset distillation framework to SNNs and event-based vision. PACE distills a large training dataset into a compact synthetic one that enables fast SNN training, which is achieved by two core modules: ST-DSM and PEQ-N. ST-DSM uses residual membrane potentials to densify spike-based features (SDR) and to perform fine-grained spatiotemporal matching of amplitude and phase (ST-SM), while PEQ-N provides a plug-and-play straight through probabilistic integer quantizer compatible with standard event-frame pipelines. Across DVS-Gesture, CIFAR10-DVS, and N-MNIST datasets, PACE outperforms existing coreset selection and dataset distillation baselines, with particularly strong gains on dynamic event streams and at low or moderate IPC. Specifically, on N-MNIST, it achieves (84.4%) accuracy, about (85%) of the full training set performance, while reducing training time by more than (50×) and storage cost by (6000×), yielding compact surrogates that enable minute-scale SNN training and efficient edge deployment.