Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks

doi:10.1002/cpe.70404

CSpace

	Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
	Chen, Shuo 1,2; Liu, Zeshi 1; You, Haihang 1
	2025-12-25
发表期刊	CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
ISSN	1532-0626
卷号	37 期号:27-28 页码:13
摘要	Spiking neural networks (SNNs) have gained significant attention due to their energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We first explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, we propose a low-cost metric to assess neuron criticality in feature transmission and design a pruning-regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26% reduction in pruning cost. The criticality-based regeneration process efficiently selects potential structures and facilitates consistent feature representation. Our code is available at
关键词	brain-inspired computing network pruning spiking neural network
DOI	10.1002/cpe.70404
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001624343100015
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/43088
专题	中国科学院计算技术研究所
通讯作者	Liu, Zeshi; You, Haihang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Shuo,Liu, Zeshi,You, Haihang. Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE,2025,37(27-28):13.
APA	Chen, Shuo,Liu, Zeshi,&You, Haihang.(2025).Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks.CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE,37(27-28),13.
MLA	Chen, Shuo,et al."Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks".CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 37.27-28(2025):13.