Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909648965074944 |
|---|---|
| author | Feng, Wanjin Gao, Xingyu Du, Wenqian Shi, Hailong Zhao, Peilin Wu, Pengcheng Miao, Chunyan |
| author_facet | Feng, Wanjin Gao, Xingyu Du, Wenqian Shi, Hailong Zhao, Peilin Wu, Pengcheng Miao, Chunyan |
| contents | 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}}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12087 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity Feng, Wanjin Gao, Xingyu Du, Wenqian Shi, Hailong Zhao, Peilin Wu, Pengcheng Miao, Chunyan Neural and Evolutionary Computing Artificial Intelligence 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}}. |
| title | Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2506.12087 |