Skip to content
Open access

Maximizing Accuracy-Per-Cost in Vehicular Federated Learning via Active Inference and Two-Stage Resource Optimization

2026 · IEEE Transactions on Network Science and Engineering · Vol 13, pp. 11399-11415 · 0 citations · 51 references
Computer Science

TL;DR

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.

Abstract

Federated Learning (FL) enables collaborative model training in the Internet of Vehicles (IoV), helping vehicles overcome data and computational limitations while preserving privacy. However, its performance is constrained by both data heterogeneity and system heterogeneity. Additionally, different FL tasks exhibit diverse preferences regarding energy consumption and end-to-end latency. To address the diverse latency and energy preferences in IoV and improve model accuracy and convergence, this paper proposes a unified framework to optimize accuracy per unit of utility in vehicular FL. Utility is modeled as a weighted sum of energy consumption and latency. We analyze key factors influencing FL model accuracy in IoV environments and establish a joint optimization problem that balances accuracy with utility cost. To match the information asymmetry between the server and clients and reduce computational complexity, we decompose the problem into two coordinated stages: server-side client selection and bandwidth allocation, and client-side computation and transmission power control. On the server side, we model decision-making as a Partially Observable Markov Decision Process (POMDP), and develop an active-inference-based actor–critic method for adaptive client selection and resource management. On the client side, we derive closed-form optimal solutions for resource allocation under heterogeneous latency and energy preferences. By combining learning-based global coordination with lightweight analytical local control, the proposed provides a practical and scalable tradeoff between adaptability, efficiency, and implementation complexity. Extensive simulations validate the effectiveness and superiority of our algorithm.

Read PDF

Similar papers

Open access 2026

Dynamic Vehicle Selection and Bandwidth Allocation for Federated Learning With Long-Term Latency Constraint in Vehicular Networks

Federated learning (FL) is increasingly adopted in vehicular networks to facilitate intelligent transportation applications while maintaining the confidentiality of onboard data. However, due to vehicle mobility, heterogeneity, and limited bandwidth resources, how to dynamically select participating vehicles and alloca...

Xiao-Na Jiang, Jie Tian, Dong-Yang Li et al. · 0 citations
Open access 2026

Mobility-Aware Multi-Model Fully Decentralized Federated Learning Framework for Vehicular Edge Computing

A mobility-aware multi-model fully decentralized federated learning (KM-MMDFL) framework is proposed that limits communication through a communication constraint and incorporates a joint peer and model exchange selection strategy to reduce communication overhead while ensuring reliable and beneficial model exchange bas...

Karnkitti Kittikamron, Natthanon Manop, Vorapong Suppakitpaisarn et al. · 0 citations
Conference Open access Sep 2026

Resource-and Data-Aware Client Selection for Heterogeneous Edge Federated Learning

This paper investigates client selection for federated learning (FL) in heterogeneous edge networks with statistical and system heterogeneity. A Resource- and Data-Aware (RDA) method is proposed to jointly consider data representativeness, training latency, energy consumption, and participation fairness. The four facto...

Jing Jin, Xin-Xin Pan · 0 citations
Open access 2026

Delay-Driven Vehicle Scheduling and Resource Optimization for Multi-Task Federated Learning in Heterogeneous Vehicular Networks

Federated learning (FL) has become a promising paradigm for privacy-preserving and communication-efficient model training in vehicular networks. With the continuous expansion of vehicular networks, multiple FL tasks are often initiated concurrently by moving vehicles, which poses substantial challenges to the conventio...

Xiao-Na Jiang, Jie Tian, Tian-Tian Li et al. · 0 citations
Open access Oct 2026

Joint Vehicle Selection and Resource Allocation for Hierarchical Federated Learning in Internet of Vehicles

Hierarchical federated learning (HFL) in the Internet of Vehicles (IoV) faces challenges in participation reliability and aggregation efficiency due to vehicle mobility and resource heterogeneity. This paper investigates joint vehicle selection and resource allocation in a three-tier HFL architecture. In this framework...

Zhen Yang, Li-Hang Wen, Wei-Jing Qi et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.