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

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.

arXiv commentTo be published in IEEE Transactions on Network and Service Management

References in corpus (15)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Wireless Communications with Unmanned Aerial Vehicles: Opportunities and Challenges
• Federated Learning for Mobile Keyboard Prediction
• Personalized Federated Learning: A Meta-Learning Approach
• Deep Reinforcement Learning for 5G Networks: Joint Beamforming, Power Control, and Interference Coordination
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
• Personalized Federated Learning with Moreau Envelopes
• Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networks
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
• A Joint Learning and Communications Framework for Federated Learning over Wireless Networks
• On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms
• Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach
• Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms
• Privacy-Preserving Federated Learning for UAV-Enabled Networks: Learning-Based Joint Scheduling and Resource Management
• A Comprehensive Overview on 5G-and-Beyond Networks with UAVs: From Communications to Sensing and Intelligence