mlsanityData to 14 Oct 2026

Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling

arXiv 2609.08312 ↗First posted 8 Sep 2026cs.IT cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

To mitigate the scalability bottleneck in the radio access network (RAN) in federated edge learning (FEEL), over-the-air federated learning (AirFL) exploits waveform superposition over multiple-access channels (MACs) for analog model aggregation. However, coherent AirFL typically relies on stringent PHY-layer conditions such as accurate channel state information (CSI), tight time/frequency synchronization, and frequent transceiver calibration for signal alignment. However, these requirements, if not impossible to be met, incur substantial communication and computation overhead. In this paper, we propose a non-coherent AirFL (NCAirFL) protocol over a broadband single-antenna MAC, leveraging binary dithering, unbiased non-coherent detection, and long-term error feedback to waive the need for instantaneous CSI. For NCAirFL with general smooth non-convex objectives and a constant learning rate, we establish a convergence bound achieving the convergence rate in the same order of O(1/√T) as communication-ideal FedAvg, where T is the total number of communication rounds. To further improve communication efficiency under data and wireless resource heterogeneity, we also derive a lower bound on the expected single-round objective decrease in the global loss conditioned on device scheduling, building upon which a surrogate objective function is obtained for jointly optimal device selection and power control. Experimental results on MNIST and CIFAR-10 corroborate that NCAirFL achieves learning performance close to FedAvg in practical settings, with the proposed device scheduling policy substantially accelerating convergence.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

27 of 40 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 724
  5. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  6. 2018Federated Learning via Over-the-Air Computationcited by 219
  7. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  8. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  9. 2019Federated Learning over Wireless Fading Channelscited by 183
  10. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 181
  11. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  12. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
15 more
  1. 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
  2. 2020Fast-Convergent Federated Learningcited by 61
  3. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
  4. 2020Blind Federated Edge Learningcited by 43
  5. 2022Gradient and Channel Aware Dynamic Scheduling for Over-the-Air Computation in Federated Edge Learning Systemscited by 20
  6. 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 14
  7. 2021Efficient Federated Meta-Learning over Multi-Access Wireless Networkscited by 13
  8. 2022Non-Coherent Over-the-Air Decentralized Gradient Descentcited by 9
  9. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learningcited by 9
  10. 2018Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flowcited by 8
  11. 2023AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memorycited by 4
  12. 2024NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detectioncited by 4
  13. 2025Biased Federated Learning under Wireless Heterogeneitycited by 4
  14. 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
  15. 2025Robust and Efficient Average Consensus with Non-Coherent Over-the-Air Aggregationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
  2. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learning
  3. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
  4. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
  5. 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
  6. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
  7. 2022Over-the-Air Federated Learning via Second-Order Optimization
  8. 2021Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels