FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels
Abstract
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.
Related
- Progressive-Resolution Secure Aggregation for Federated Learning
- Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm
- Green Learning-Based Signal-Level Detection of RIS Spoofing Attacks in Vehicular ISAC Systems
- On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression
- Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation
BibTeX
@misc{yan2026fedpgt,
title = {{FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels}},
author = {Jintao Yan and Tan Chen and Yuxuan Sun and Sheng Zhou and Zhisheng Niu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18089},
eprint = {2609.18089},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18089},
}
RIS
TY - UNPB
TI - FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels
AU - Jintao Yan
AU - Tan Chen
AU - Yuxuan Sun
AU - Sheng Zhou
AU - Zhisheng Niu
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18089
UR - https://arxiv.org/abs/2609.18089
AB - 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.
ER -