Cluster-Aware Over-the-Air Federated Learning with Energy-Harvesting Devices: From Global Training to Model Personalization

2026-08-02

AI Summary

This work addresses the challenge of balancing global model representativeness and user-specific personalization in federated learning under practical constraints such as data heterogeneity, limited communication resources, and the stochastic energy supply of energy-harvesting devices. To this end, the authors propose a unified over-the-air computation (AirComp) framework driven by clustering. For the first time, this framework integrates user clustering structure into energy-aware scheduling and AirComp receiver design. By incorporating cluster-aware user selection, energy-diversity-aware mechanisms, joint signal recovery over multi-access channels, and cluster-level model training, the approach enables a synergistic optimization of fairness and personalization. Experimental results demonstrate that the proposed method significantly reduces communication overhead while effectively enhancing either model fairness or personalization performance, depending on the operational mode.

Abstract

Federated learning (FL) enables distributed optimization and learning across decentralized edge devices while preserving data privacy, but its performance is fundamentally constrained by heterogeneous data distributions, limited communication resources, and energy availability. In practical wireless networks, mobile devices (MDs) often exhibit diverse data and learning objectives, naturally forming clusters of users with jointly trainable models. When devices rely on energy harvesting (EH), stochastic energy arrivals further complicate participation and scheduling under communication constraints. In this work, we study over-the-air (OTA) FL with EH MDs under heterogeneous data distributions, and investigate two closely related learning objectives within a unified framework: one aiming for a more representative global model by reducing data bias, and the other learning more personalized cluster-specific models by exploiting this bias. In the global training mode, cluster information guides energy- and diversity-aware scheduling, ensuring that the scheduled active users provide a more representative aggregate update. In the personalization mode, the same cluster structure defines cluster-level learning objectives and OTA recovery targets, enabling the parameter server to train multiple cluster-specific models through simultaneous transmissions over the wireless multiple-access channel. Numerical results demonstrate that the proposed unified framework improves fairness or personalization, depending on the operating mode, while reducing communication overhead.

Problem

• Federated Learning
• Energy Harvesting
• Over-the-Air Computation
• Data Heterogeneity
• Model Personalization

Innovation

• cluster-aware
• over-the-air federated learning
• energy harvesting
• model personalization
• heterogeneous data