{
  "abstract": "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.08312",
  "author_total": 5,
  "authors": [
    {
      "name": "Haifeng Wen"
    },
    {
      "name": "Nicolò Michelusi"
    },
    {
      "name": "Osvaldo Simeone"
    },
    {
      "name": "Yang Yang"
    },
    {
      "name": "Hong Xing"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dy1j19b7g3ac4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.08312",
  "fulltext_url": null,
  "id": "dy1j19b7g3ac4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.08312",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1702|Privacy-Preserving Technologies in Data"
    ]
  ],
  "openalex": "W7212057650",
  "pdf_url": "https://arxiv.org/pdf/2609.08312",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dy1j19b7g3ac4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:58Z",
      "native_id": "2609.08312",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.08312"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling",
  "title_text": "Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:58Z",
  "url": "https://research.draconitic.com/paper/dy1j19b7g3ac4",
  "venue": "arXiv",
  "versions": []
}