Constrained Over-the-Air Model Updating for Wireless Online Federated Learning with Delayed Information

2025-01-10

AI Summary

This paper addresses the joint optimization of latency-aware control, dynamic power constraints, and over-the-air computation (AirComp) in wireless online federated learning. We propose a Lyapunov-drift-based joint control framework. Key contributions include: (1) a novel low–upper-bound virtual queue mechanism that rigorously enforces hard per-slot power constraints under latency information; (2) an extended Lyapunov drift analysis that jointly upper-bounds dynamic/static regret and constraint violations; and (3) a closed-form local update policy enabling bandwidth-efficient and robust global model aggregation under time-varying channels. Evaluated on image classification tasks, the proposed method significantly outperforms state-of-the-art approaches in low-power regimes, achieving substantial accuracy gains. Crucially, our theoretical analysis guarantees that constraint violations remain strictly bounded—providing rigorous feasibility assurances absent in prior works.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Online Learning & Bandits
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

We study online federated learning over a wireless network, where the central server updates an online global model sequence to minimize the time-varying loss of multiple local devices over time. The server updates the global model through over-the-air model-difference aggregation from the local devices over a noisy multiple-access fading channel. We consider the practical scenario where information on both the local loss functions and the channel states is delayed, and each local device is under a time-varying power constraint. We propose Constrained Over-the-air Model Updating with Delayed infOrmation (COMUDO), where a new lower-and-upper-bounded virtual queue is introduced to counter the delayed information and control the hard constraint violation. We show that its local model updates can be efficiently computed in closed-form expressions. Furthermore, through a new Lyapunov drift analysis, we show that COMUDO provides bounds on the dynamic regret, static regret, and hard constraint violation. Simulation results on image classification tasks under practical wireless network settings show substantial accuracy gain of COMUDO over state-of-the-art approaches, especially in the low-power region.

Problem

• Wireless Networks
• Online Collaborative Learning
• Energy Efficiency

Innovation

• COMUDO
• Online Collaborative Learning
• Power-efficient Image Recognition