针对边缘联邦学习中设备异构问题，提出自适应压缩与计算优化方案。
Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compression
- 根据设备异构性动态调整更新频率和压缩率
- 在保持高精度的同时降低延迟与能耗
- 适合资源受限的移动边缘网络场景
针对云基联邦学习的不足，协同边缘联邦学习（CFEL）被提出以提升移动边缘网络中的分布式模型训练效率。然而，动态且异构的设备特性导致收敛缓慢、资源消耗大。本文提出一种异构感知的协同边缘联邦平均算法（HCEF），通过自适应计算与通信压缩，在最大化模型精度的同时最小化训练时延和能耗。基于理论分析本地更新频率与梯度压缩对收敛误差的影响，设计了高效的在线控制算法，动态分配异构设备的更新频率与压缩比。实验表明，相较于现有方法，所提HCEF在保持更高模型精度的同时，显著降低训练延迟并提升能效。
原文摘要 · Abstract (English)
Motivated by the drawbacks of cloud-based federated learning (FL), cooperative federated edge learning (CFEL) has been proposed to improve efficiency for FL over mobile edge networks, where multiple edge servers collaboratively coordinate the distributed model training across a large number of edge devices. However, CFEL faces critical challenges arising from dynamic and heterogeneous device properties, which slow down the convergence and increase resource consumption. This paper proposes a heterogeneity-aware CFEL scheme called \textit{Heterogeneity-Aware Cooperative Edge-based Federated Averaging} (HCEF) that aims to maximize the model accuracy while minimizing the training time and energy consumption via adaptive computation and communication compression in CFEL. By theoretically analyzing how local update frequency and gradient compression affect the convergence error bound in CFEL, we develop an efficient online control algorithm for HCEF to dynamically determine local update frequencies and compression ratios for heterogeneous devices. Experimental results show that compared with prior schemes, the proposed HCEF scheme can maintain higher model accuracy while reducing training latency and improving energy efficiency simultaneously.
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。