CoChat

Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

Open access
Elgabli, Anis, Park, Jihong, Issaid, Chaouki Ben, Bennis, Mehdi · 2021 · IEEE Transactions on Communications

The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.

Abstract

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker’s model update while multiple workers’ updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coinedanalog federated ADMM (A-FADMM)based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker’s exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tcomm.2021.3078783

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Schematic illustrations of: (a) digital federated learning (FL), (b) analog FL with channel inversion, and (c) analogfederated ADMM (A-FADMM) without channel inversion.
Fig. 1 Schematic illustrations of: (a) digital federated learning (FL), (b) analog FL with channel inversion, and (c) analogfederated ADMM (A-FADMM) without channel inversion.CC-BY · From the PDF
Fig. 2 An illustration of uplink and downlink communication in A-FADMM under channel noise.
Fig. 2 An illustration of uplink and downlink communication in A-FADMM under channel noise.CC-BY · From the PDF
Image 3
CC-BY · From the PDF
Image 4
CC-BY · From the PDF
Image 5
CC-BY · From the PDF
Image 6
CC-BY · From the PDF
Fig. 6 Impact of the number of local iterations in image classification using DNNs.
Fig. 6 Impact of the number of local iterations in image classification using DNNs.CC-BY · From the PDF
Fig. 7 Impact of the learning rate in image classification using DNNs.
Fig. 7 Impact of the learning rate in image classification using DNNs.CC-BY · From the PDF
Image 9
CC-BY · From the PDF
Image 10
CC-BY · From the PDF
Image 11
CC-BY · From the PDF
Image 12
CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 37 references

Research works printed but not linked: 5

  1. 10.1109/JPROC.2019.2917084 · DOI
  2. torgo, 2014, Regression DataSets
  3. glowinski, 1975, Sur l’approximation, par éléments finis d’ordre un, et al. résolution, par pénalisation-dualité d’une classe de problèmes de dirichlet non linéaires, ESAIM Math Modelling Numer Anal -Modélisation Mathématique et Analyse Numérique, 9, 41
  4. goodfellow, 2014, Generative adversarial nets, Proc Adv Neural Inf Process Syst, 27
  5. 2017, 5G NR Physical channels and modulation

Cited by

See all 15

Metadata

Authors
Elgabli, A., Park, J., Issaid, C. B., & Bennis, M.
Affiliations
  • University of Oulu (FI)
  • Deakin University (AU)
Venue
IEEE Transactions on Communications
Published
2021-08
Volume
69
Issue
8
Pages
5194-5208
ISSN
  • 0090-6778 (ISSN-L)
  • 1558-0857
OpenAlex
W3038145895
Cited by
14
References
37
Citations by year
2024: 1 · 2023: 1 · 2022: 2 · 2021: 8
FWCI
1.06
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Communications (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • Deakin Research Online (Deakin University) (submittedVersion)
  • Figshare (submittedVersion, cc-by)
  • arXiv (Cornell University)
Funders
  • Academy of Finland 6G Flagship (318927)
  • project SMARTER, projects EU-ICT IntellIoT (957218)
  • EUCHISTERA LearningEdge, Infotech-NOOR
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Wireless Communication Security Techniques
Keywords
federated learning, wireless channels, channel randomness, interference, privacy preservation, model inversion attacks, over-the-air aggregation, analog signal transmission, alternating direction method of multipliers, spectral efficiency, scalability, honest-but-curious server, eavesdropping, convergence analysis, non-convex optimization, energy efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning. https://app.cochat.ai/papers/10.1109/tcomm.2021.3078783
The paper
Elgabli, A., Park, J., Issaid, C. B., & Bennis, M. (2021). Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning. IEEE Transactions on Communications. https://doi.org/10.1109/tcomm.2021.3078783

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.