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 is proposed, establishing a convergence bound that characterizes the impact of transmitted gradient entries and reveals diminishing-return behavior governed by a power-law decay.
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.
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.
Thieu Van Nguyen, T. Nguyen, Ons Aouedi et al.· 0 citations
The Cognitive Federated Graph Learning (CFGL) framework is introduced to jointly optimise three interdependent resources in cognitive radio networks: (i) frequency channel allocation for secondary-user transmissions, (ii) routing paths for multi-hop packet traversal, and (iii) transmit-power budgets as determined by pe...
Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting waveform superposition for simultaneous model aggregation. Most existing work struggles with heterogeneous fading channels. These approaches either enforce unbiased up...
Ming Xiang, Nicolò Michelusi, Y. Eldar et al.· ACM Interational Symposium o...· 0 citations
A federated random walk averaging framework is proposed, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server and reduces the problem to a general form agnostic to task type and model architecture.
Chang-Heng Wang, Xian-Chao Zhang, Zhi-Qing Wei et al.· 0 citations
A unified framework to optimize accuracy per unit of utility in vehicular FL, combining learning-based global coordination with lightweight analytical local control is proposed, providing a practical and scalable tradeoff between adaptability, efficiency, and implementation complexity.
Xiang-Qing Su, Yan Huo, Zi-Han Chen et al.· IEEE Transactions on Network...· 0 citations
Experimental results demonstrate that the proposed framework improves convergence, accuracy, scalability, and signal-to-noise ratio, data rate, while simultaneously reducing latency, and energy consumption for both CIFAR-10 and FEMNIST datasets compared with the FedProx, FedADMM, LyFeD and FL-MEC benchmark schemes.
Kofi Kwarteng Abrokwa, Qi Jiang, Zhou-Qin Ma et al.· IEEE Transactions on Green C...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026