发表机构
Polytechnique Montreal（蒙特利尔理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对二值化神经网络剪枝适配问题，提出基于PyTorch的专用框架及全局加权剪枝算法，在VGG11二值化模型上实现70%剪枝率且准确率不变，优于现有最优结果。
AI 中文摘要
深度神经网络的极致压缩，直至完全二值化，可大幅减少内存占用与算术复杂度，便于在带有现场可编程门阵列（FPGAs）和微控制器的受限边缘硬件上部署。尽管将二值化与剪枝结合有望进一步提升效率，但现有剪枝策略并不适配二值化表示，且极少能转化为实际硬件节省。我们提出一种基于PyTorch、面向研究的框架，该框架集成了冻结与剪枝机制，用于设计和优化二值化神经网络。此框架支持对现有最优方法进行快速可复现评估，并能快速原型化新方法。借助该框架，我们提出一种新型剪枝方法，该方法考虑了不同抽象层级上学到参数的相对重要性。这种全局加权机制在模型准确率与剪枝率之间始终实现更优权衡，在VGG11上达到70%的剪枝率且准确率保持不变，而在二值化设置下，现有最优结果仅达到41%。
英文摘要
Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating deployment on constrained edge hardware with field-programmable gate arrays (FPGAs) and microcontrollers. Although combining binarization with pruning promises additional efficiency gains, existing pruning strategies are ill-suited to binarized representations and rarely translate into meaningful hardware savings. We introduce a PyTorch-based, research-oriented framework that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks. The framework enables rapid and reproducible evaluation of state-of-the-art approaches and the fast prototyping of new ones. Leveraging this framework, we propose a novel pruning method that accounts for the relative importance of learned parameters across abstraction levels. Such a global weighting mechanism consistently achieves a superior trade-off between model accuracy and pruning rate, achieving a 70% pruning rate on VGG11 with constant accuracy, while state-of-the-art results reach only 41% in the binarized setting.
Comments9 pages, 3 figures, 5 tables, 3 algorithms
