UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach

TL;DR

This paper presents a hierarchical federated learning framework utilizing UAV swarms to enable personalized, resource-efficient machine learning across geo-distributed, resource-constrained device clusters with dynamic data distributions.

Contribution

It introduces a novel hierarchical nested personalized federated learning approach combined with UAV swarm cooperation and deep reinforcement learning for system optimization.

Findings

Improved ML performance with resource savings

Effective handling of data heterogeneity and concept drift

Optimized UAV swarm trajectories for efficiency

Abstract

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.