Coherence-Aware Over-the-Air Distributed Learning under Heterogeneous Link Impairments

TL;DR

This paper introduces a coherence-aware federated learning framework that improves over-the-air distributed training in wireless networks with heterogeneous link impairments by optimizing channel estimation and model aggregation strategies.

Contribution

It proposes a novel OFDM super-block partitioning and pilot multiplexing scheme that adapts to varying coherence times and bandwidths, enhancing communication efficiency and learning stability.

Findings

Significant reduction in communication overhead.

Improved convergence and accuracy in heterogeneous wireless environments.

Enhanced robustness to channel estimation errors.

Abstract

Distributed machine learning (ML) over wireless networks hinges on accurate channel state information (CSI) and efficient exchange of high-dimensional model updates. These demands are governed by channel coherence time and bandwidth, which vary across devices (links) due to heterogeneous mobility and scattering, causing degraded downlink delivery and distorted uplink over-the-air (OTA) aggregation. We propose a coherence-aware federated learning (FL) framework that jointly addresses impairments on downlink and uplink with communication-efficient strategies. In the downlink, we employ product superposition to multiplex global model symbols for long-coherence (static) devices onto the pilot tones required by short-coherence (dynamic) devices for channel estimation, turning pilot overhead into payload while preserving estimation fidelity. In the proposed scheme, an orthogonal frequency-division multiplexing (OFDM) super-block is partitioned into sub-blocks aligned with the smallest coherence time and bandwidth, enabling consistent channel estimation and stabilizing OTA aggregation across heterogeneous devices. Partial model reception at dynamic devices is mitigated via previous local model filling (PLMF), which reuses prior updates. We establish convergence guarantees under heterogeneous link impairments, imperfect CSI, and aggregation noise. The proposed framework enables efficient scheduling under coherence heterogeneity; analysis and experiments demonstrate notable gains in communication efficiency, latency, and learning accuracy over conventional FL baselines.