Sensing-Native Over-the-Air Federated Learning

2026-06-15

AI Summary

This work addresses the resource competition and degraded learning performance in conventional integrated sensing, communication, and computation-enabled over-the-air federated learning (AirFL), which typically allocates dedicated resources for sensing. To overcome this limitation, the paper proposes a natively integrated AirFL framework that exploits the autocorrelation properties of local gradient signals to enable zero-overhead ranging and leverages gradient statistics to achieve cooperative localization concurrently with model aggregation—without requiring additional communication resources. The core contributions include a sensing mechanism based on matched filtering and trilateration, a closed-form optimal power allocation strategy, and a successive convex approximation-based beamforming optimization. Extensive simulations demonstrate that the proposed approach significantly outperforms existing baselines in both learning accuracy and sensing precision.

Abstract

Over-the-air federated learning (FL) leverages the superposition property of multiple-access channels to enable communication-efficient distributed model training. Existing integrated sensing, communication, and computation (ISCC)-enabled over-the-air FL systems typically require dedicated resources for the sensing module, inevitably compromising FL performance due to resource competition. In this paper, we propose a sensing-native over-the-air FL framework that explores built-in distributed wireless sensing capability with zero overhead per model aggregation. Specifically, the high-dimensional local gradient signals possessing favorable autocorrelation property are concurrently leveraged for target distance estimation, while the gradient statistics already required for over-the-air FL serve as a ready-made gateway to deliver locally-sensed results to the edge server for cooperative localization. To combat inter-device interference, channel fading, and communication noise, we put forth a robust trilateration-based target positioning method building upon an efficient matched-filtering-based distance estimation. Then, by explicitly characterizing the impact of imperfect model aggregation and noisy gradient-statistics transmission on the sensing-native over-the-air FL convergence, we develop a statistics-aware communication-learning co-design approach. We first derive the closed-form optimal power budgets allocated to local gradients and their statistics, based on which an efficient successive convex approximation method is proposed for receiver beamforming optimization. Simulation results show that the proposed framework simultaneously achieves superior learning and sensing performance compared to representative baselines.

Problem

• Over-the-Air Federated Learning
• Integrated Sensing and Communication
• Resource Competition
• Distributed Wireless Sensing
• Model Aggregation

Innovation

• Sensing-Native
• Over-the-Air Federated Learning
• Integrated Sensing and Communication
• Matched Filtering
• Communication-Learning Co-Design