mlsanityData to 14 Oct 2026

BASC : Behavior-Aligned Quantization and Pruning for Low-Bit Spiking Neural Networks

arXiv 2608.19239 ↗First posted 12 Aug 2026cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) encode information through binary spikes and compute in an event-driven manner, offering an energy-efficient paradigm for machine intelligence. However, high-performance SNNs incur substantial memory and timestep-wise computation costs that hinder deployment on resource-constrained devices. Quantization and pruning provide complementary routes to reducing these costs, yet both make their decisions with local criteria that overlook temporal task feedback in quantization and inter-channel dependencies in pruning. Consequently, optimizing either criterion can still yield suboptimal compression performance. We refer to this discrepancy as criterion-behavior mismatch and propose Behavior-Aligned SNN Compression (BASC), a unified framework with two lightweight modules. For quantization, the scale is applied to synaptic current at every timestep and therefore shifts spike timing. Temporal-Behavior Scale Correction (TSC) makes the scale learnable under a temporal loss, allowing firing behavior to inform scale optimization. For pruning, channel importance depends on how channels jointly drive the membrane potential across the firing threshold. Boundary-Level Inter-Channel Correction (BIC) uses channelwise importance scores for initial selection and inter-channel information to re-evaluate only channels near the pruning threshold. Extensive experiments on static and neuromorphic benchmarks show that lower-bit BASC models match or outperform higher-bit baselines and retain this accuracy advantage after structured pruning, while further reducing model storage and synaptic operations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

18 of 40 references.

References · 18

  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  4. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  5. 2019Learned Step Size Quantizationcited by 628
  6. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  7. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  8. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
  9. 2021Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networkscited by 78
  10. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
  11. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 46
  12. 2019Comprehensive SNN Compression Using ADMM Optimization and Activity Regularizationcited by 45
6 more
  1. 2019Optimizing the energy consumption of spiking neural networks for neuromorphic applicationscited by 37
  2. 2021Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networkscited by 21
  3. 2023DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processorcited by 21
  4. 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 10
  5. 2022Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimatorcited by 4
  6. 2024Fast Switching Serial and Parallel Paradigms of SNN Inference on Multi-core Heterogeneous Neuromorphic Platform SpiNNaker2cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Spiking Brain Compression: Post-Training Second-order Compression for Spiking Neural Networks
  2. 2025QP-SNN: Quantized and Pruned Spiking Neural Networks
  3. 2026PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
  4. 2023Is Conventional SNN Really Efficient? A Perspective from Network Quantization
  5. 2026Quantization of Spiking Neural Networks Beyond Accuracy
  6. 2023The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks
  7. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networks
  8. 2024Q-SNNs: Quantized Spiking Neural Networks