基于剪枝的轻量级联邦智能学习算法  

A Lightweight Federated Intelligence Learning Algorithm Based on Pruning

作　　者：张泰宁 汤子娇 ZHANG Taining;TANG Zijiao(The 54th Research Institute of China Eectronics Tchnology Group Corporation,Shijiazhuang 050081,China;Arizona College of Technology,Hebei University of Technology,Tianjin 300401,Chnia)

机构地区：[1]中国电子科技集团第54研究所,石家庄050081 [2]河北工业大学亚利桑那工业学院,天津300401

出　　处：《计算机测量与控制》2025年第4期292-298,305,共8页Computer Measurement &Control

摘　　要：针对深度学习模型中工作节点异构性导致的训练效率低下和全局模型准确性无法保证的问题,提出了一种基于剪枝的轻量级联邦学习框架FedPrune;采用“教师-学生模型”架构,通过自适应剪枝方案从全局基础模型中动态生成适应不同工作节点能力的子模型,实现轻量级的智能算法在资源受限的设备中高效执行,并提出动态自适应剪枝率学习方法,使各工作节点在相互不知晓能力的情况下实现相同更新时间;与两种本地解决方案FedAVG、FedRC和两种全局解决方案FedAsync、SSP算法在CIFAR10、CIFAR100、Tiny-ImageNet数据集上进行对比实验,FedPrune具有更高的准确性和更短的总体时间;FedPrune框架通过动态生成适应不同工作节点能力的子模型,有效解决了掉队问题,并在异构环境中保持了高精度和高速度,证明了其在联邦学习中的效率和适用性。Aiming at the problems of low training efficiency and unguaranteed global model accuracy caused by the heterogeneity of work nodes in deep learning models,a lightweight federated learning framework based on pruning,FedPrune,is proposed.Adopting the“teacher-student model”architecture,the adaptive pruning scheme dynamically generates sub-models adapted to the capabilities of different work nodes from the global base model,realizes the efficient execution of lightweight intelligent algorithms in resource-constrained devices,and proposes a dynamic adaptive pruning rate learning method,so that work nodes achieve the same updating time without knowing each other's capabilities,to realize the same update time without knowing each other's capability.The algorithms are implemented with the two local solutions,FedAVG and FedRC,and the two global solutions,FedAsync and SSP,in the CIFAR10,CIFAR100,and Tiny-ImageNet datasets for comparison experiments,FedPrune has higher accuracy and shorter overall time.The FedPrune framework effectively solves the dropout problem by dynamically generating submodels adapted to the capabilities of different working nodes,and maintains high accuracy and speed in heterogeneous environments,proving its efficiency and applicability in federated learning.

关 键 词：深度学习 联邦学习 教师-学生模型 自适应剪枝 剪枝率学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]