arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.14946cs.LG
收藏

脉冲层自适应幅度剪枝

Spiking Layer-Adaptive Magnitude-based Pruning

Sichuan University-Pittsburgh Institute(四川大学匹兹堡研究院);Sichuan University(四川大学);College of Computer Science(计算机科学学院)

Junqiao Wang, Zhehang Ye, Yuqi Ouyang

AI总结:

本文提出SLAMP框架,通过时间扭曲约束优化实现时间感知层重要性评分,有效减少连接和脉冲操作,保持精度,实现高效可部署的SNN推理。

摘要:

脉冲神经网络(SNNs)提供高效计算但受限于密集连接和高脉冲操作成本。现有基于幅度的剪枝策略在SNNs中应用时未能考虑时间累积、非均匀时间步贡献和膜稳定性,常导致性能下降。本文提出SLAMP,一种理论指导的剪枝框架,通过显式控制层间和时间步的最坏输出扭曲,将层自适应幅度剪枝推广到时间SNNs。SLAMP将稀疏分配建模为时间扭曲约束优化问题,得到时间感知的层重要性评分,在单时间步极限下退化为传统层自适应剪枝。推导出高效的两阶段流程,结合时间分数估计、全局稀疏分配和幅度剪枝,并通过重训练恢复稳定性。在CIFAR10、CIFAR100和事件基CIFAR10-DVS数据集上的实验表明,SLAMP在减少连接和脉冲操作的同时保持精度,实现高效可部署的SNN推理。

英文摘要:

Spiking Neural Networks (SNNs) provide energy-efficient computation but their deployment is constrained by dense connectivity and high spiking operation costs. Existing magnitude-based pruning strategies, when naively applied to SNNs, fail to account for temporal accumulation, non-uniform timestep contributions, and membrane stability, often leading to severe performance degradation. This paper proposes Spiking Layer-Adaptive Magnitude-based Pruning (SLAMP), a theory-guided pruning framework that generalizes layer-adaptive magnitude pruning to temporal SNNs by explicitly controlling worst-case output distortion across layers and timesteps. SLAMP formulates sparsity allocation as a temporal distortion-constrained optimization problem, yielding time-aware layer importance scores that reduce to conventional layer-adaptive pruning in single-timestep limit. An efficient two-stage procedure is derived, combining temporal score estimation, global sparsity allocation, and magnitude pruning with retraining for stability recovery. Experiments on CIFAR10, CIFAR100, and the event-based CIFAR10-DVS datasets demonstrate that SLAMP achieves substantial connectivity and spiking operation reductions while preserving accuracy, enabling efficient and deployable SNN inference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑