通过协同多种剪枝信号，实现模型各层精准压缩，显著降低精度损失。
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
- 基于敏感度分析与架构规则，分层生成多样剪枝策略
- 在Swin-Tiny上使精度损失减少40%（相对单准则剪枝）
- 无需重复实验，直接输出可部署的压缩方案
将深度神经网络（DNN）部署于边缘设备需要强压缩且保持最小精度损失。本文提出混合匹配剪枝（Mix-and-Match Pruning），一种全局引导的分层稀疏化框架，利用敏感度评分与简单架构规则生成多样化、高质量的剪枝配置。该框架解决了不同层和架构对剪枝响应差异大的问题，单一策略往往效果不佳。通过推导架构感知的稀疏度范围（如保留归一化层，更激进地剪枝分类器），并系统采样这些范围，每种敏感度信号（幅度、梯度或其组合）可生成十种策略。该方法避免重复剪枝训练，直接提供部署就绪的精度-稀疏度权衡方案。在CNN与视觉变换器（Vision Transformers）上的实验表明，该方法达到帕累托最优性能，相比标准单准则剪枝，使Swin-Tiny的精度损失降低40%。结果表明，协调已有剪枝信号比引入新准则更能实现可靠高效的压缩模型。
原文摘要 · Abstract (English)
Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity scores and simple architectural rules to generate diverse, high-quality pruning configurations. The framework addresses a key limitation that different layers and architectures respond differently to pruning, making single-strategy approaches suboptimal. Mix-and-Match derives architecture-aware sparsity ranges, e.g., preserving normalization layers while pruning classifiers more aggressively, and systematically samples these ranges to produce ten strategies per sensitivity signal (magnitude, gradient, or their combination). This eliminates repeated pruning runs while offering deployment-ready accuracy-sparsity trade-offs. Experiments on CNNs and Vision Transformers demonstrate Pareto-optimal results, with Mix-and-Match reducing accuracy degradation on Swin-Tiny by 40% relative to standard single-criterion pruning. These findings show that coordinating existing pruning signals enables more reliable and efficient compressed models than introducing new criteria.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。