Temporal-adaptive Weight Quantization for Spiking Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 14 Nov 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networks
- 2023Is Conventional SNN Really Efficient? A Perspective from Network Quantization
- 2024Q-SNNs: Quantized Spiking Neural Networks
- 2024SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks
- 2026PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
- 2025Memory-Free and Parallel Computation for Quantized Spiking Neural Networks
- 2025Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
- 2023Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function