针对移动设备带来的网络波动，提出动态压缩策略提升联邦学习效率
Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification
- 根据设备接触时长和模型过时程度自适应调整梯度压缩比例
- 在CIFAR-10上准确率提升8.76%，轨迹预测误差降低9.46%
- 适用于高速移动场景下的稳定联邦学习，适合移动端部署
异步联邦学习（AFL）允许多个移动设备独立更新本地模型，无需等待其他设备。然而，设备移动性导致连接间歇性，迫使采用梯度稀疏化，同时引发模型过时问题，共同影响AFL的收敛性。本文建立理论模型，刻画稀疏化、模型过时与移动引起的接触模式之间的相互作用及其对收敛的影响。基于分析结果，提出一种面向移动性的动态稀疏化（MADS）算法，依据接触时间与模型过时程度优化稀疏化程度。推导出闭式解表明：低速条件下，增加稀疏化以加速收敛；高速条件下，减少稀疏化以确保在有限接触时间内可靠上传。实验验证了理论发现。相比现有最优基准，MADS在CIFAR-10图像分类任务上准确率提升8.76%，在Argoverse轨迹预测数据集上平均位移误差降低9.46%。
原文摘要 · Abstract (English)
Asynchronous Federated Learning (AFL) enables distributed model training across multiple mobile devices, allowing each device to independently update its local model without waiting for others. However, device mobility introduces intermittent connectivity, which necessitates gradient sparsification and leads to model staleness, jointly affecting AFL convergence. This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns, and their joint impact on AFL convergence. Based on the analysis, we propose a mobility-aware dynamic sparsification (MADS) algorithm that optimizes the sparsification degree based on contact time and model staleness. Closed-form solutions are derived, showing that under low-speed conditions, MADS increases the sparsification degree to enhance convergence, while under high-speed conditions, it reduces the sparsification degree to guarantee reliable uploads within limited contact time. Experimental results validate the theoretical findings. Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIFAR-10 dataset by 8.76% and reduces the average displacement error in the Argoverse trajectory prediction dataset by 9.46%.
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。