Integrated user scheduling and beam steering in over-the-air federated learning for mobile IoT

2025-08-01

AI Summary

To address the challenges of scarce radio resources, limited user participation, and high aggregation errors in over-the-air federated learning (OTA-FL) for mobile Internet-of-Things (IoT), this paper proposes an iterative optimization framework jointly designing user scheduling and receive beamforming. The non-convex joint optimization problem is reformulated via difference-of-convex (DC) programming and solved using a low-complexity, channel-state-information (CSI)-aware scheduling strategy. The method simultaneously enhances over-the-air computation (AirComp) aggregation accuracy and communication efficiency under constraints on the number of participating users and transmit power. Experiments demonstrate that, compared to state-of-the-art approaches, the proposed method reduces model aggregation error by approximately 32% and improves test accuracy by 2.1–4.7 percentage points. It effectively balances communication overhead, privacy preservation, and learning performance in resource-constrained mobile IoT environments.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The rising popularity of Internet of things (IoT) has spurred technological advancements in mobile internet and interconnected systems. While offering flexible connectivity and intelligent applications across various domains, IoT service providers must gather vast amounts of sensitive data from users, which nonetheless concomitantly raises concerns about privacy breaches. Federated learning (FL) has emerged as a promising decentralized training paradigm to tackle this challenge. This work focuses on enhancing the aggregation efficiency of distributed local models by introducing over-the-air computation into the FL framework. Due to radio resource scarcity in large-scale networks, only a subset of users can participate in each training round. This highlights the need for effective user scheduling and model transmission strategies to optimize communication efficiency and inference accuracy. To address this, we propose an integrated approach to user scheduling and receive beam steering, subject to constraints on the number of selected users and transmit power. Leveraging the difference-of-convex technique, we decompose the primal non-convex optimization problem into two sub-problems, yielding an iterative solution. While effective, the computational load of the iterative method hampers its practical implementation. To overcome this, we further propose a low-complexity user scheduling policy based on characteristic analysis of the wireless channel to directly determine the user subset without iteration. Extensive experiments validate the superiority of the proposed method in terms of aggregation error and learning performance over existing approaches.

Problem

• Enhance FL aggregation efficiency via over-the-air computation
• Optimize user scheduling and beam steering in resource-limited IoT
• Reduce computational load in FL with low-complexity scheduling

Innovation

• Over-the-air computation for FL aggregation
• Integrated user scheduling and beam steering
• Low-complexity channel-based user scheduling