Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Shu, Yu, Chengting, Liu, Lei, Ma, Hanzhi, Wang, Aili, Li, Erping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913749296742400
author Yang, Shu
Yu, Chengting
Liu, Lei
Ma, Hanzhi
Wang, Aili
Li, Erping
author_facet Yang, Shu
Yu, Chengting
Liu, Lei
Ma, Hanzhi
Wang, Aili
Li, Erping
contents Spiking Neural Networks (SNNs) have garnered considerable attention as a potential alternative to Artificial Neural Networks (ANNs). Recent studies have highlighted SNNs' potential on large-scale datasets. For SNN training, two main approaches exist: direct training and ANN-to-SNN (ANN2SNN) conversion. To fully leverage existing ANN models in guiding SNN learning, either direct ANN-to-SNN conversion or ANN-SNN distillation training can be employed. In this paper, we propose an ANN-SNN distillation framework from the ANN-to-SNN perspective, designed with a block-wise replacement strategy for ANN-guided learning. By generating intermediate hybrid models that progressively align SNN feature spaces to those of ANN through rate-based features, our framework naturally incorporates rate-based backpropagation as a training method. Our approach achieves results comparable to or better than state-of-the-art SNN distillation methods, showing both training and learning efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
Yang, Shu
Yu, Chengting
Liu, Lei
Ma, Hanzhi
Wang, Aili
Li, Erping
Machine Learning
Artificial Intelligence
Spiking Neural Networks (SNNs) have garnered considerable attention as a potential alternative to Artificial Neural Networks (ANNs). Recent studies have highlighted SNNs' potential on large-scale datasets. For SNN training, two main approaches exist: direct training and ANN-to-SNN (ANN2SNN) conversion. To fully leverage existing ANN models in guiding SNN learning, either direct ANN-to-SNN conversion or ANN-SNN distillation training can be employed. In this paper, we propose an ANN-SNN distillation framework from the ANN-to-SNN perspective, designed with a block-wise replacement strategy for ANN-guided learning. By generating intermediate hybrid models that progressively align SNN feature spaces to those of ANN through rate-based features, our framework naturally incorporates rate-based backpropagation as a training method. Our approach achieves results comparable to or better than state-of-the-art SNN distillation methods, showing both training and learning efficiency.
title Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.16572