UAV-Assisted Online Machine Learning Over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach

We investigate training machine learning (ML) models across a set of geo-distributed, resource-constrained clusters of devices through unmanned aerial vehicles (UAV) swarms. The presence of time-varying data heterogeneity and computational resource inadequacy among device clusters motivate four key parts of our methodology: (i) stratified UAV swarms of leader, worker, and coordinator UAVs, (ii) hierarchical nested personalized federated learning (HN-PFL), a distributed ML framework for personalized model training across the worker-leader-core network hierarchy, (iii) cooperative UAV resource pooling to address computational inadequacy of devices by conducting model training among the UAV swarms, and (iv) model/concept drift to model time-varying data distributions. In doing so, we consider both micro (i.e., UAV-level) and macro (i.e., swarm-level) system design. At the micro-level, we propose network-aware HN-PFL, where we distributively orchestrate UAVs inside swarms to optimize energy consumption and ML model performance with performance guarantees. At the macro-level, we focus on swarm trajectory and learning duration design, which we formulate as a sequential decision making problem tackled via deep reinforcement learning. Our simulations demonstrate the improvements achieved by our methodology in terms of ML performance, network resource savings, and swarm trajectory efficiency.

Automated summary

In this study, we train machine learning models on geo-distributed, resource-constrained clusters of devices through unmanned aerial vehicle (UAV) swarms. We address the challenges posed by varying data heterogeneity and computational resource inadequacy among device clusters by introducing stratified UAV swarms, hierarchical nested personalized federated learning (HN-PFL), cooperative UAV resource pooling, and model/concept drift. Our methodology considers both micro and macro system design, with a focus on network-aware HN-PFL and swarm trajectory and learning duration design tackled via deep reinforcement learning. Simulations demonstrate the effectiveness of our approach in terms of ML performance, resource savings, and swarm trajectory efficiency.