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

• URL: http://arxiv.org/abs/2602.15326v1
• Date: Tue, 17 Feb 2026 03:13:32 GMT
• Title: SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillation
• Abstract summary: SCENE is a pilot-free and phase-invariant aggregation primitive for over-the-air federated distillation (OTA-FD)<n>It trades a modest noncoherent variance constant for zero uplink pilots, unbiased aggregation, and hardware-friendly transmission.<n>It can outperform coherent designs when pilot overhead is non-negligible.
• Score: 5.14549984289357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets [51.490743278360064]
  We propose a trajectory-based DD framework that jointly suppresses noise and preserves transferable knowledge without relabeling or clean subsets.<n>It comprises two complementary components: Selective Guidance Reweighting (SGR) and Teacher-Inspired Auxiliary Targets (TIAT)
  arXiv  Detail & Related papers  (2026-06-29T06:24:53Z)
• Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation [16.23840462167471]
  Decentralized Federated Learning enables collaborative model training across wireless edge nodes.<n>We propose DFL-AA, which corrects selection bias using Inverse Probability Weighting and mitigates staleness via Age-of-Information decay.<n>We prove that DFL-AA removes link-quality distortion in expectation and consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-09T12:30:18Z)
• Coverage Analysis of Rydberg Atom Quantum Receiver Arrays: A Stochastic Geometry Approach [55.47164192369501]
  Rydberg atomic quantum receivers (RAQRs) offer quantum-limited sensitivity and broadband tunability.<n>In dense deployments, aggregate interference can push atomic transducer out of its small-signal regime.<n>This paper addresses the question by embedding the RAQR front end into a geometry coverage analysis.
  arXiv  Detail & Related papers  (2026-05-22T04:05:13Z)
• Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning [5.14549984289357]
  Over-the-air federated learning (OTA-FL) reduces uplink latency by exploiting waveform superposition.<n>Conventional analog aggregation schemes typically require channel state information (CSI), channel inversion, and coherent phase alignment.
  arXiv  Detail & Related papers  (2026-05-08T05:29:14Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous Data [12.4809003470908]
  FCO achieves communication efficiency and robustness when dealing with non-smoothizers.<n>Fed Composite Error FeedbackCEF is a novel algorithm for non-efficient quant convergence.<n>It mitigates the noise from aggressiveization and the noise from non-IID data.
  arXiv  Detail & Related papers  (2026-03-08T14:37:16Z)
• Interference-Robust Non-Coherent Over-the-Air Computation for Decentralized Optimization [8.071989780397692]
  Non-coherent over-the-air (NCOTA) computation enables low-latency and bandwidth-efficient decentralized optimization.<n>In this paper, we propose a novel interference-robust (IR-)NCOTA scheme.
  arXiv  Detail & Related papers  (2026-02-12T21:30:51Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Joint Embedding Variational Bayes [0.08594140167290097]
  Variational Joint Embedding (VJE) is a framework that synthesizes joint embedding and variational inference.<n>VJE enables self-supervised learning of probabilistic representations in a reconstruction-free, non-contrastive setting.
  arXiv  Detail & Related papers  (2026-02-05T13:18:53Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• OptiVote: Non-Coherent FSO Over-the-Air Majority Vote for Communication-Efficient Distributed Federated Learning in Space Data Centers [68.73273027298625]
  megaconstellations are driving the long-term vision of space data centers (SDCs)<n>AirComp is an in-network aggregation framework for learning free-space (FSO)<n>AirVote integrates sign gradient (SGD) with a majority-signposition modulation (PPM), where each satellite conveys local gradient by activating PPM time slots.<n>OptiVote mitigates phase-sensitive field superposition into phase-agnostic optical intensity combining.
  arXiv  Detail & Related papers  (2025-12-30T16:40:02Z)
• Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off [6.832750677765499]
  Over-the-air (OTA) convex learning (FL) has been well recognized as a scalable paradigm that exploits the superposition of the wireless multiple-access channel to model updates in a single use.<n>We develop novel OTAFL SGD updates that allow a structured bias, however, facilitating reduced gradient updates.
  arXiv  Detail & Related papers  (2025-10-30T17:22:57Z)
• SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation [10.159672026403097]
  Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data.<n>We propose SteeringTTA, an inference-only framework that adapts Feynman-Kac steering to guide diffusion-based input adaptation for classification with rewards driven by pseudo-label.
  arXiv  Detail & Related papers  (2025-10-16T12:46:53Z)
• Improving Black-Box Generative Attacks via Generator Semantic Consistency [51.470649503929344]
  generative attacks produce adversarial examples in a single forward pass at test time.<n>We enforce semantic consistency by aligning the early generator's intermediate features to an EMA teacher.<n>Our approach can be seamlessly integrated into existing generative attacks with consistent improvements in black-box transfer.
  arXiv  Detail & Related papers  (2025-06-23T02:35:09Z)
• Non-Coherent Over-the-Air Decentralized Gradient Descent [0.0]
  Implementing Decentralized Gradient Descent in wireless systems is challenging due to noise, fading, and limited bandwidth. This paper introduces a scalable DGD algorithm that eliminates the need for scheduling, topology information, or CSI.
  arXiv  Detail & Related papers  (2022-11-19T19:15:34Z)
• Over-the-Air Federated Learning from Heterogeneous Data [107.05618009955094]
  Federated learning (FL) is a framework for distributed learning of centralized models. We develop a Convergent OTA FL (COTAF) algorithm which enhances the common local gradient descent (SGD) FL algorithm. We numerically show that the precoding induced by COTAF notably improves the convergence rate and the accuracy of models trained via OTA FL.
  arXiv  Detail & Related papers  (2020-09-27T08:28:25Z)
• Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms [98.78553146823829]
  Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks. In this paper, a novel framework is proposed to implement distributed learning (FL) algorithms within a UAV swarm.
  arXiv  Detail & Related papers  (2020-02-19T14:04:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.