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

2026-02-16

AI Summary

This work addresses the limitations of conventional over-the-air federated distillation (OTA-FD) in short-coherence-time and hardware-constrained settings, where reliance on channel state information (CSI) incurs high pilot overhead. To overcome this, the authors propose SCENE—a pilot-free, phase-invariant, self-centering noncoherent estimator. SCENE maps soft labels to constant-envelope, non-negative energy signals, employs a self-centering mechanism to eliminate noise-induced energy bias, and introduces ratio normalization to cancel unknown large-scale fading. Combined with multi-antenna receive diversity, this approach enables unbiased model aggregation without CSI. Notably, SCENE achieves the first pilot-free OTA-FD framework that is both hardware-friendly and communication-efficient, with its aggregation error variance decaying at a rate of 1/(SM), where M is the number of antennas and S the repetition factor—significantly outperforming coherent schemes when pilot overhead is non-negligible.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Non-convex Optimization
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Large-scale security measurements

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.

Problem

• over-the-air federated distillation
• noncoherent aggregation
• pilot-free
• hardware-constrained
• channel state information

Innovation

• over-the-air federated distillation
• pilot-free
• noncoherent estimation
• self-centering estimator
• constant-envelope signaling