AI 中文总结
针对脉冲神经网络压缩的准则-行为不匹配问题，提出含TSC、BIC模块的BASC框架，可实现低位SNN性能匹配或优于高位基线，同时降低存储与计算开销。
AI 中文摘要
脉冲神经网络（SNN）通过二元尖峰编码信息并以事件驱动方式计算，为机器智能提供了一种高能效范式。然而，高性能SNN会产生大量内存和逐时间步计算开销，阻碍其在资源受限设备上的部署。量化与剪枝是降低这些开销的互补途径，但二者均基于局部准则做决策，量化时忽略了时序任务反馈，剪枝时忽略了通道间依赖关系。因此，优化任一准则仍可能产生次优的压缩性能，我们将这种差异称为“准则-行为不匹配”，并提出行为对齐SNN压缩（BASC）框架，该框架包含两个轻量模块。对于量化，缩放因子应用于每个时间步的突触电流，从而改变尖峰时间；时序行为缩放校正（TSC）使缩放因子在时序损失下可学习，让发放行为为缩放优化提供指导。对于剪枝，通道重要性取决于通道共同驱动膜电位超过发放阈值的程度；边界级通道间校正（BIC）使用逐通道重要性分数进行初始选择，再利用通道间信息仅重新评估接近剪枝阈值的通道。在静态和神经形态基准上的大量实验表明，低位BASC模型的性能与高位基线相当或更优，且在结构化剪枝后仍保留该精度优势，同时进一步减少了模型存储和突触操作。
英文摘要
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.
