QP-SNN: Quantized and Pruned Spiking Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Wenjie, Zhang, Malu, Zhou, Zijian, Belatreche, Ammar, Shan, Yimeng, Liang, Yu, Cao, Honglin, Zhang, Jieyuan, Yang, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912418590883840
author Wei, Wenjie
Zhang, Malu
Zhou, Zijian
Belatreche, Ammar
Shan, Yimeng
Liang, Yu
Cao, Honglin
Zhang, Jieyuan
Yang, Yang
author_facet Wei, Wenjie
Zhang, Malu
Zhou, Zijian
Belatreche, Ammar
Shan, Yimeng
Liang, Yu
Cao, Honglin
Zhang, Jieyuan
Yang, Yang
contents Brain-inspired Spiking Neural Networks (SNNs) leverage sparse spikes to encode information and operate in an asynchronous event-driven manner, offering a highly energy-efficient paradigm for machine intelligence. However, the current SNN community focuses primarily on performance improvement by developing large-scale models, which limits the applicability of SNNs in resource-limited edge devices. In this paper, we propose a hardware-friendly and lightweight SNN, aimed at effectively deploying high-performance SNN in resource-limited scenarios. Specifically, we first develop a baseline model that integrates uniform quantization and structured pruning, called QP-SNN baseline. While this baseline significantly reduces storage demands and computational costs, it suffers from performance decline. To address this, we conduct an in-depth analysis of the challenges in quantization and pruning that lead to performance degradation and propose solutions to enhance the baseline's performance. For weight quantization, we propose a weight rescaling strategy that utilizes bit width more effectively to enhance the model's representation capability. For structured pruning, we propose a novel pruning criterion using the singular value of spatiotemporal spike activities to enable more accurate removal of redundant kernels. Extensive experiments demonstrate that integrating two proposed methods into the baseline allows QP-SNN to achieve state-of-the-art performance and efficiency, underscoring its potential for enhancing SNN deployment in edge intelligence computing.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QP-SNN: Quantized and Pruned Spiking Neural Networks
Wei, Wenjie
Zhang, Malu
Zhou, Zijian
Belatreche, Ammar
Shan, Yimeng
Liang, Yu
Cao, Honglin
Zhang, Jieyuan
Yang, Yang
Computer Vision and Pattern Recognition
Brain-inspired Spiking Neural Networks (SNNs) leverage sparse spikes to encode information and operate in an asynchronous event-driven manner, offering a highly energy-efficient paradigm for machine intelligence. However, the current SNN community focuses primarily on performance improvement by developing large-scale models, which limits the applicability of SNNs in resource-limited edge devices. In this paper, we propose a hardware-friendly and lightweight SNN, aimed at effectively deploying high-performance SNN in resource-limited scenarios. Specifically, we first develop a baseline model that integrates uniform quantization and structured pruning, called QP-SNN baseline. While this baseline significantly reduces storage demands and computational costs, it suffers from performance decline. To address this, we conduct an in-depth analysis of the challenges in quantization and pruning that lead to performance degradation and propose solutions to enhance the baseline's performance. For weight quantization, we propose a weight rescaling strategy that utilizes bit width more effectively to enhance the model's representation capability. For structured pruning, we propose a novel pruning criterion using the singular value of spatiotemporal spike activities to enable more accurate removal of redundant kernels. Extensive experiments demonstrate that integrating two proposed methods into the baseline allows QP-SNN to achieve state-of-the-art performance and efficiency, underscoring its potential for enhancing SNN deployment in edge intelligence computing.
title QP-SNN: Quantized and Pruned Spiking Neural Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.05905