SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillation

TL;DR

This paper introduces SCENE, a pilot-free, phase-invariant estimator for over-the-air federated distillation that enables unbiased aggregation without channel state information, especially suited for hardware-constrained environments.

Contribution

The paper presents SCENE, a novel noncoherent estimator for OTA-FD that eliminates the need for pilots and large-scale gain calibration, with proven unbiasedness and favorable variance properties.

Findings

SCENE achieves unbiased soft-label aggregation without uplink pilots.

Variance of the estimator decreases with more antennas and repetitions.

Outperforms coherent methods when pilot overhead is significant.

Abstract

We propose SCENE (Self-Centering Noncoherent Estimator), a pilot-free and phase-invariant aggregation primitive for over-the-air federated distillation (OTA-FD). Each device maps its soft-label (class-probability) vector to nonnegative transmit energies under constant per-round power and constant-envelope signaling (PAPR near 1). At the server, a self-centering energy estimator removes the noise-energy offset and yields an unbiased estimate of the weighted soft-label average, with variance decaying on the order of 1/(SM) in the number of receive antennas M and repetition factor S. We also develop a pilot-free ratio-normalized variant that cancels unknown large-scale gains, provide a convergence bound consistent with coherent OTA-FD analyses, and present an overhead-based crossover comparison. SCENE targets short-coherence and hardware-constrained regimes, where avoiding per-round CSI is essential: it trades a modest noncoherent variance constant for zero uplink pilots, unbiased aggregation, and hardware-friendly transmission, and can outperform coherent designs when pilot overhead is non-negligible.