Metraipolis › archive › dc_83ed0ea55051
Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling — arXiv:2609.08312
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08312
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:30.288Z
- SHA-256 of the archived text
563433b209bb7cf5458ff21c652e503a572acb163b921130916afb392161636e- Stable URL of this page
https://metraipolis.com/documento/dc_83ed0ea55051
How to cite
Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling — arXiv:2609.08312 — arXiv (en), https://arxiv.org/abs/2609.08312 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83ed0ea55051 (Metraipolis archive dc_83ed0ea55051, sha256 563433b209bb7cf5458ff21c652e503a572acb163b921130916afb392161636e)
BibTeX
@misc{dc83ed0ea55051,
title = {Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling — arXiv:2609.08312},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08312},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83ed0ea55051; sha256 563433b209bb7cf5458ff21c652e503a572acb163b921130916afb392161636e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08312. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 $\mathcal{O}(1/\sqrt{T})$ 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.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Information Theory (cs.IT) ; Machine Learning (cs.LG); Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.08312 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.270Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).