Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' data, and the computation and communication latency increase when updating large-scale learning models on devices with limited computational capability and wireless resources. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device, which adapts the model size during FL to reduce both computation and communication latency and increases the learning accuracy for devices with non-independent and identically distributed data. The computation and communication latency and convergence of the proposed FL framework are mathematically analyzed. To maximize the convergence rate and guarantee learning accuracy, Karush Kuhn Tucker (KKT) conditions are deployed to jointly optimize the pruning ratio and bandwidth allocation. Finally, experimental results demonstrate that the proposed FL framework achieves a remarkable reduction of approximately 50 percent computation and communication latency compared with FL with partial model personalization.

翻译：联邦学习（FL）支持在边缘设备上实现分布式学习，同时保护数据隐私。然而，设备数据的异构性会降低学习精度，且在计算能力和无线资源受限的设备上更新大规模学习模型时，计算与通信时延会增大。本文提出一种结合部分模型剪枝与个性化的联邦学习框架以应对这些挑战。该框架将学习模型分为两部分：全局部分（通过模型剪枝与所有设备共享，用于学习数据表征）和个性化部分（针对特定设备进行微调）。该方法在联邦学习过程中自适应调整模型大小，从而降低计算与通信时延，并提升非独立同分布数据设备的学习精度。本文从数学上分析了所提联邦学习框架的计算时延、通信时延及收敛性。为最大化收敛速率并保证学习精度，采用Karush Kuhn Tucker（KKT）条件联合优化剪枝比例与带宽分配。实验结果表明，与仅采用部分模型个性化的联邦学习相比，所提框架可实现计算与通信时延约50%的显著降低。