SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillation
This work addresses the challenge of efficient communication in federated learning for scenarios with limited coherence time and hardware constraints, though it is incremental as it builds on existing OTA-FD methods.
The paper tackles the problem of over-the-air federated distillation in short-coherence and hardware-constrained regimes by proposing SCENE, a pilot-free and phase-invariant aggregation method that avoids per-round channel state information, resulting in unbiased aggregation with variance decaying on the order of 1/(SM).
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.