Temporal-adaptive Weight Quantization for Spiking Neural Networks
Neural and Evolutionary Computing
2025-11-25 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Abstract
Weight quantization in spiking neural networks (SNNs) could further reduce energy consumption. However, quantizing weights without sacrificing accuracy remains challenging. In this study, inspired by astrocyte-mediated synaptic modulation in the biological nervous systems, we propose Temporal-adaptive Weight Quantization (TaWQ), which incorporates weight quantization with temporal dynamics to adaptively allocate ultra-low-bit weights along the temporal dimension. Extensive experiments on static (e.g., ImageNet) and neuromorphic (e.g., CIFAR10-DVS) datasets demonstrate that our TaWQ maintains high energy efficiency (4.12M, 0.63mJ) while incurring a negligible quantization loss of only 0.22% on ImageNet.
Keywords
Cite
@article{arxiv.2511.17567,
title = {Temporal-adaptive Weight Quantization for Spiking Neural Networks},
author = {Han Zhang and Qingyan Meng and Jiaqi Wang and Baiyu Chen and Zhengyu Ma and Xiaopeng Fan},
journal= {arXiv preprint arXiv:2511.17567},
year = {2025}
}