基于AdamW梯度跟踪的弹性分布式无线联邦学习
Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW
浏览论文内容
中文总结 AI 辅助
本文提出QEF-GT-AdamW算法，结合梯度跟踪、AdamW优化与带误差反馈的双流偏置量化，解决无线分布式学习的通信开销与不可靠传输问题，在异构数据集上实现更优性能。
中文摘要 AI 辅助
无线物联网（IoT）边缘网络需要能在异构本地数据和通信受限无线链路下可靠运行的分布式学习（DecL）方法。但现有分布式优化方案在受严格空口预算、衰落信道和丢包限制的传输场景中，往往会产生大量通信开销并导致性能下降。本文提出QEF-GT-AdamW，一种用于无线通信（WCom）网络上DecL的通信高效且抗中断的算法。该方法结合梯度跟踪以缓解非独立同分布（non-IID）数据的影响、基于AdamW的自适应优化以提升训练稳定性，以及带误差反馈的双流偏置量化以减少模型和跟踪交互的通信负载。为应对不可靠的广播通信，所提框架在调度数据包未成功接收时采用本地 fallback 策略。我们明确建模带宽、发射功率、空口约束和衰落信道对DecL性能的影响，并在压缩且不可靠的无线通信下为所提算法建立收敛保证。在异构MNIST和CIFAR-10设置上的实验结果表明，QEF-GT-AdamW在有限无线资源下，相比代表性DecL基线始终提升了鲁棒性和收敛性能，同时实现了良好的准确率-通信权衡。
英文摘要
Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing decentralized optimization schemes often incur substantial communication overhead and degraded performance when transmissions are constrained by strict airtime budgets, fading channels, and packet losses. This paper proposes QEF-GT-AdamW, a communication-efficient and outage-resilient algorithm for DecL over wireless communication (WCom) networks. The proposed method combines gradient tracking to mitigate the effect of non-IID data, AdamW-based adaptive optimization to improve training stability, and dual-stream biased quantization with error feedback to reduce communication payloads for both model and tracking exchanges. To address unreliable broadcast communication, the proposed framework further employs a local fallback strategy when scheduled packets are not successfully received. We explicitly model the effect of bandwidth, transmit power, airtime constraints, and fading channels on DecL performance, and establish convergence guarantees for the proposed algorithm under compressed and unreliable wireless communication. Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.
发表机构
- University of Luxembourg（卢森堡大学）
- Interdisciplinary Centre for Security, Reliability and Trust (SnT)（安全、可靠性与跨学科信任中心（SnT））
机构由 AI 辅助整理，请以论文原文为准。
