# SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

arXiv: https://arxiv.org/abs/2312.17216 · HTML: https://mlsanity.com/paper/2312.17216/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 87 references that are in the map.
- First posted on arXiv 28 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks](https://mlsanity.com/paper/2302.13939/) (2023)
- [Object Detection with Spiking Neural Networks on Automotive Event Data](https://mlsanity.com/paper/2205.04339/) (2022)
- [Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks](https://mlsanity.com/paper/2009.08378/) (2020)
- [Fast and energy-efficient neuromorphic deep learning with first-spike times](https://mlsanity.com/paper/1912.11443/) (2019)
- [Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardware](https://mlsanity.com/paper/1601.04187/) (2016)
- [A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks](https://mlsanity.com/paper/1907.02649/) (2019)
- [Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time](https://mlsanity.com/paper/2112.11231/) (2021)
- [Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks](https://mlsanity.com/paper/2212.01232/) (2022)
- [Training Spiking Deep Networks for Neuromorphic Hardware](https://mlsanity.com/paper/1611.05141/) (2016)
- [Smooth Exact Gradient Descent Learning in Spiking Neural Networks](https://mlsanity.com/paper/2309.14523/) (2023)
- [Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators](https://mlsanity.com/paper/2206.01338/) (2022)
- [Balanced networks of spiking neurons with spatially dependent recurrent connections](https://mlsanity.com/paper/1308.6014/) (2013)
- [Dynamics and computation in mixed networks containing neurons that accelerate towards spiking](https://mlsanity.com/paper/1812.09218/) (2018)
- [Event-based Backpropagation for Analog Neuromorphic Hardware](https://mlsanity.com/paper/2302.07141/) (2023)

## Built on by (most cited first, 6 of 6)

- [Exploring the Limitations of Layer Synchronization in Spiking Neural Networks](https://mlsanity.com/paper/2408.05098/) (2024)
- [EventFlash: Towards Efficient MLLMs for Event-Based Vision](https://mlsanity.com/paper/2602.03230/) (2026)
- [Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness](https://mlsanity.com/paper/2503.17394/) (2025)
- [Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks](https://mlsanity.com/paper/2603.13283/) (2026)
- [Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent](https://mlsanity.com/paper/2606.03935/) (2026)
- [Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection](https://mlsanity.com/paper/2607.09115/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) are biologically-inspired models that are capable of processing information in streams of action potentials. However, simulating and training SNNs is computationally expensive due to the need to solve large systems of coupled differential equations. In this paper, we introduce SparseProp, a novel event-based algorithm for simulating and training sparse SNNs. Our algorithm reduces the computational cost of both the forward and backward pass operations from O(N) to O(log(N)) per network spike, thereby enabling numerically exact simulations of large spiking networks and their efficient training using backpropagation through time. By leveraging the sparsity of the network, SparseProp eliminates the need to iterate through all neurons at each spike, employing efficient state updates instead. We demonstrate the efficacy of SparseProp across several classical integrate-and-fire neuron models, including a simulation of a sparse SNN with one million LIF neurons. This results in a speed-up exceeding four orders of magnitude relative to previous event-based implementations. Our work provides an efficient and exact solution for training large-scale spiking neural networks and opens up new possibilities for building more sophisticated brain-inspired models.