Personalized Federated Learning by Energy-Efficient UAV Communications

2026-05-24

AI Summary

This work addresses the challenges of slow convergence due to data heterogeneity in geographically distributed federated learning and the high energy consumption caused by full-device communication in UAV-assisted settings. To mitigate these issues, the authors propose an architecture that strictly decouples a shared backbone network from personalized heads, effectively alleviating the adverse effects of data heterogeneity. Additionally, they introduce a device scheduling mechanism based on the ℓ₂ norm of local gradients, wherein only the top-α devices with the largest gradient norms participate in backbone updates during each communication round. This approach significantly reduces UAV communication energy consumption while simultaneously accelerating model convergence and improving accuracy, thereby achieving a synergistic optimization of energy efficiency and learning performance.

Abstract

Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically dispersed FL systems, such as sensor networks in remote areas, unmanned aerial vehicles (UAVs) can flexibly establish high-quality communication links to support parameter exchange. However, device heterogeneity and the limited battery capacity of UAVs pose significant challenges. Specifically, data heterogeneity slows convergence, while scheduling all devices for global collaboration incurs excessive communication and energy costs. To overcome these challenges, we adopt a strict separation between a globally shared backbone and permanently local personalization heads, thereby mitigating the impact of data heterogeneity. Furthermore, we propose a gradient-based scheduling strategy that jointly considers energy efficiency and learning performance. In each communication round, the backbone is updated only by the top-$α$ devices ranked by gradient $\ell_{2}$-norm, ensuring that optimization focuses on the most informative updates. Simulation results demonstrate that the proposed scheme achieves higher learning accuracy than state-of-the-art approaches while significantly reducing UAV energy consumption.

Problem

• Federated Learning
• Data Heterogeneity
• UAV Energy Efficiency
• Device Scheduling
• Personalized Learning

Innovation

• Personalized Federated Learning
• UAV Communications
• Gradient-based Scheduling
• Energy Efficiency
• Data Heterogeneity