Domain-Aware Hierarchical Federated Learning for UAV Swarms Across Heterogeneous Environments
Authors: Taha Mahmood, Mudassar Shakeel, Ahmed Naeem, El Mehdi Amhoud, Rizwan Ahmad, Salman Ghafoor
Organizations: School of Electrical Engineering and Computer Science, National University of Sciences and Technology, 44000, Islamabad, Pakistan. · College of Computing, University Mohammed VI Polytechnic, Benguerir 43150, Morocco
Hierarchical federated learning (HFL) enables communication-efficient training in unmanned aerial vehicle (UAV) swarms, but performance degrades under changing and heterogeneous environments. This paper proposes domain-aware HFL (DA-HFL), integrating mobility-informed clustering, cluster-level aggregation, cloud-based Fisher-weighted merging, a domain-adversarial shared backbone, environment-specific heads, and gated inference with local adaptation. A mission-weighted optimization formulation incorporates energy, latency, and cluster-head eligibility constraints. Theoretical analysis establishes resource feasibility, a conditional backbone-stationarity bound, the quadratic optimality of Fisher-weighted merging, and communication and computation complexity bounds. Simulations across four heterogeneous environments demonstrate faster convergence, improved accuracy during environmental transitions, and more stable, purer clusters than the evaluated baselines, with modest energy overhead over resource-aware HFL. Ablation studies validate the contributions of the proposed components.
Figures & tables
Fig. 1: Overall architecture of the proposed domain-aware hierarchical federated learning framework for mobile UAV swarms.
Fig. 2: (a) global test accuracy vs. communication rounds, (b) global training loss vs. communication rounds and (c) accuracy with temporal error bars.
Hierarchical Federated Learning organizes collaborative model training across clients, edge nodes, and central servers to reduce communication and handle data diversity.