Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity

TL;DR

This paper introduces a fixed-point parallel training method for spiking neural networks that reduces training time complexity from linear to constant, enabling faster training without accuracy loss.

Contribution

The paper presents a novel FPT method that achieves constant time complexity in SNN training, with theoretical convergence proof and practical efficiency improvements.

Findings

FPT reduces training complexity from O(T) to O(K) with K=3.

Experimental results confirm FPT's accuracy and efficiency in simulating LIF neuron dynamics.

FPT significantly accelerates training for long-term SNN tasks without accuracy degradation.

Abstract

Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive. In this paper, we propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture or introducing additional assumptions. FPT reduces the time complexity to $O(K)$, where $K$ is a small constant (usually $K=3$), by using a fixed-point iteration form of Leaky Integrate-and-Fire (LIF) neurons for all $T$ timesteps. We provide a theoretical convergence analysis of FPT and demonstrate that existing parallel spiking neurons can be viewed as special cases of our proposed method. Experimental results show that FPT effectively simulates the dynamics of original LIF neurons, significantly reducing computational time without sacrificing accuracy. This makes FPT a scalable and efficient solution for real-world applications, particularly for long-term tasks. Our code will be released at \href{https://github.com/WanjinVon/FPT}{\texttt{https://github.com/WanjinVon/FPT}}.