Federated learning~(FL) facilitates the training and deploying AI models on edge devices. Preserving user data privacy in FL introduces several challenges, including expensive communication costs, limited resources, and data heterogeneity. In this paper, we propose SPATL, an FL method that addresses these issues by: (a) introducing a salient parameter selection agent and communicating selected parameters only; (b) splitting a model into a shared encoder and a local predictor, and transferring its knowledge to heterogeneous clients via the locally customized predictor. Additionally, we leverage a gradient control mechanism to further speed up model convergence and increase robustness of training processes. Experiments demonstrate that SPATL reduces communication overhead, accelerates model inference, and enables stable training processes with better results compared to state-of-the-art methods. Our approach reduces communication cost by up to $86.45\%$, accelerates local inference by reducing up to $39.7\%$ FLOPs on VGG-11, and requires $7.4 \times$ less communication overhead when training ResNet-20.
翻译:联邦学习-(FL)促进边际装置培训和应用AI模型; 在边际装置中保护用户数据隐私提出了若干挑战,包括昂贵的通信费用、有限的资源和数据差异性; 本文提出SPATL, 一种解决这些问题的FL方法,即:(a) 引入一个显著参数选择剂,仅传达选定的参数;(b) 将一个模型分成一个共用编码器和一个本地预测器,并通过当地定制的预测器将其知识传递给不同客户; 此外,我们利用梯度控制机制,进一步加快模式趋同,提高培训过程的稳健性; 实验表明SPATL降低了通信费,加快了模型推断速度,使稳定的培训过程能够取得比最新方法更好的结果; 我们的方法将通信费用降低至86.45 美元,通过将VGG-11上的FLOP降低到39.7 $FLOP, 加速当地推导速度,在培训ResNet-20时将通信费降低7.4美元。