FedPGT：时变信道下车联网联邦学习的渐进式梯度传输
FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels
- Beijing Jiaotong University（北京交通大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对车联网联邦学习在时变信道下通信开销高的问题，提出渐进式梯度传输方案FedPGT，通过按瞬时信道渐进传输高幅值梯度并采用李雅普诺夫在线调度，在CIFAR-10和Argoverse任务上分别提升准确率3.65%和降低位移误差12.66%。
AI中文摘要：
车联网联邦学习（VFL）能够为智能交通系统实现保护隐私的协作模型训练，其中通信资源分配和梯度稀疏化技术已被探索用于降低通信开销。然而，车辆移动性导致信道条件和传输容量快速变化，使得预先确定的资源分配和稀疏化决策失效。在本文中，我们提出了FedPGT，一种用于时变信道下VFL的渐进式梯度传输方案，其中车辆根据瞬时信道条件渐进式地传输高幅值梯度条目。我们建立了一个收敛界，刻画了所传输梯度条目的影响，并揭示了由幂律衰减控制的收益递减行为。受此结果启发，我们为在线决策制定了一个随机优化问题，其主要挑战在于一个累积耦合、不可分离的目标函数。为应对这一挑战，我们引入了每时隙的替代传输变量来解耦跨时隙的长期依赖，并将原始目标转化为可加性的每时隙优化问题，从而能够采用李雅普诺夫漂移加惩罚方法进行在线调度。我们进一步开发了一种低复杂度的资源分配算法，以实现高效的在线实施。实验结果表明，与最先进的基线相比，所提出的方案在CIFAR-10图像分类任务上实现了3.65%的准确率提升，在Argoverse轨迹预测任务上实现了平均位移误差12.66%的降低，展示了其在高度动态车辆环境下对多样化学习任务的适用性。
英文摘要：
Vehicular federated learning (VFL) enables privacy-preserving collaborative model training for intelligent transportation systems, where communication resource allocation and gradient sparsification techniques have been explored to reduce communication overhead. However, vehicle mobility leads to rapidly varying channel conditions and transmission capacity, rendering predetermined resource allocation and sparsification decisions ineffective. In this paper, we propose FedPGT, a progressive gradient transmission scheme for VFL over time-varying channels, where vehicles progressively transmit high-magnitude gradient entries in response to instantaneous channel conditions. We establish a convergence bound that characterizes the impact of transmitted gradient entries and reveals diminishing-return behavior governed by a power-law decay. Motivated by this result, we formulate a stochastic optimization problem for online decision-making, where the main challenge lies in a cumulatively coupled, non-separable objective. To handle this challenge, we introduce per-slot surrogate transmission variables to decouple the long-term dependence across time slots and convert the original objective into an additive per-slot optimization problem, enabling a Lyapunov drift-plus-penalty approach for online scheduling. We further develop a low-complexity resource allocation algorithm for efficient online implementation. Experimental results demonstrate that the proposed scheme achieves a 3.65% accuracy improvement on the CIFAR-10 image classification task and a 12.66% reduction in average displacement error on the Argoverse trajectory prediction task compared with state-of-the-art baselines, demonstrating its applicability to diverse learning tasks under highly dynamic vehicular environments.
