Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

VR-VFL: Joint Rate and Client Selection for Vehicular Federated Learning Under Imperfect CSI

Metehan Karatas, Subhrakanti Dey, Christian Rohner, Jose Mairton Barros da Silva

TL;DR

This work tackles federated learning over vehicular edge networks under imperfect, time-varying CSI by introducing VR-VFL, a joint rate selection and client scheduling framework with flexible round timing. It models the wireless channel as a Gauss-Markov process to capture mobility-induced I-CSI, and formulates a bi-objective optimization that balances learning convergence against round duration, solved via a convergent block coordinate descent method. Empirical results on CIFAR-10 show VR-VFL reduces training time by about 40-43% to reach the same accuracy as fixed-round baselines, with gains in both IID and non-IID data scenarios. The approach advances practical FL in vehicular environments by explicitly accounting for mobility, data heterogeneity, and realistic wireless constraints, and the authors provide open-source code for replication.

Abstract

Federated learning in vehicular edge networks faces major challenges in efficient resource allocation, largely due to high vehicle mobility and the presence of imperfect channel state information. Many existing methods oversimplify these realities, often assuming fixed communication rounds or ideal channel conditions, which limits their effectiveness in real-world scenarios. To address this, we propose variable rate vehicular federated learning (VR-VFL), a novel federated learning method designed specifically for vehicular networks under imperfect channel state information. VR-VFL combines dynamic client selection with adaptive transmission rate selection, while also allowing round times to flex in response to changing wireless conditions. At its core, VR-VFL is built on a bi-objective optimization framework that strikes a balance between improving learning convergence and minimizing the time required to complete each round. By accounting for both the challenges of mobility and realistic wireless constraints, VR-VFL offers a more practical and efficient approach to federated learning in vehicular edge networks. Simulation results show that the proposed VR-VFL scheme achieves convergence approximately 40% faster than other methods in the literature.

VR-VFL: Joint Rate and Client Selection for Vehicular Federated Learning Under Imperfect CSI

TL;DR

This work tackles federated learning over vehicular edge networks under imperfect, time-varying CSI by introducing VR-VFL, a joint rate selection and client scheduling framework with flexible round timing. It models the wireless channel as a Gauss-Markov process to capture mobility-induced I-CSI, and formulates a bi-objective optimization that balances learning convergence against round duration, solved via a convergent block coordinate descent method. Empirical results on CIFAR-10 show VR-VFL reduces training time by about 40-43% to reach the same accuracy as fixed-round baselines, with gains in both IID and non-IID data scenarios. The approach advances practical FL in vehicular environments by explicitly accounting for mobility, data heterogeneity, and realistic wireless constraints, and the authors provide open-source code for replication.

Abstract

Federated learning in vehicular edge networks faces major challenges in efficient resource allocation, largely due to high vehicle mobility and the presence of imperfect channel state information. Many existing methods oversimplify these realities, often assuming fixed communication rounds or ideal channel conditions, which limits their effectiveness in real-world scenarios. To address this, we propose variable rate vehicular federated learning (VR-VFL), a novel federated learning method designed specifically for vehicular networks under imperfect channel state information. VR-VFL combines dynamic client selection with adaptive transmission rate selection, while also allowing round times to flex in response to changing wireless conditions. At its core, VR-VFL is built on a bi-objective optimization framework that strikes a balance between improving learning convergence and minimizing the time required to complete each round. By accounting for both the challenges of mobility and realistic wireless constraints, VR-VFL offers a more practical and efficient approach to federated learning in vehicular edge networks. Simulation results show that the proposed VR-VFL scheme achieves convergence approximately 40% faster than other methods in the literature.
Paper Structure (15 sections, 1 theorem, 19 equations, 5 figures)

This paper contains 15 sections, 1 theorem, 19 equations, 5 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Channel Model
  4. Signal Model
  5. Learning Model
  6. Successful Transmission Condition
  7. Client Participation and Rate Selection
  8. Convergence Analysis
  9. Problem Formulation
  10. Solution to Problem $\mathcal{P}$
  11. Simulation Results
  12. Simulation parameters
  13. Numerical Results
  14. Conclusion
  15. Proof of Lemma \ref{['lemma:objectiveFunctionConvexity']}

Key Result

Lemma 1

Consider the optimization problem $\mathcal{P}$ given in eq:optimizationProblem2. The objective function in Eq. eq:objective2 is convex with respect to the variables $\mathbf{R}_t$.

Figures (5)

  • Figure 1: The FL operation, where four vehicles update their locally trained models to the RSUs, then the base station aggregates the models and broadcasts the new global model.
  • Figure 2: Test accuracy for VR-VFL for different $\alpha$ (IID).
  • Figure 3: Test accuracy for VR-VFL for different $\alpha$ (non-IID).
  • Figure 4: Test accuracy for VR-VFL, Scheme 1 [6] and Scheme 2 [6].
  • Figure 5: Test accuracy for VR-VFL, Scheme 1 [6] and Scheme 2 [6].

Theorems & Definitions (2)

  • Lemma 1
  • proof