Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 173

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Optimized Power Control Design for Over-the-Air Federated Edge Learning

Open access
Cao, Xiaowen, Zhu, Guangxu, Xu, Jie, Wang, Zhiqin, Cui, Shuguang · 2022 · IEEE Journal on Selected Areas in Communications

Abstract

Over-the-air federated edge learning(Air-FEEL) has emerged as a communication-efficient solution to enable distributed machine learning over edge devices by using their data locally to preserve the privacy. By exploiting the waveform superposition property of wireless channels, Air-FEEL allows the “one-shot” over-the-air aggregation of gradient-updates to enhance the communication efficiency, but at the cost of a compromised learning performance due to the aggregation errors caused by channel fading and noise. This paper investigates the transmission power control to combat against such aggregation errors in Air-FEEL. Different from conventional power control designs (e.g., to minimize the individualmean squared error(MSE) of the over-the-air aggregation at each round), we consider a new power control design aiming at directly maximizing the convergence speed. Towards this end, we first analyze the convergence behavior of Air-FEEL (in terms of the optimality gap) subject to aggregation errors at different communication rounds. It is revealed that if the aggregation estimates are unbiased, then the training algorithm would converge exactly to the optimal point with mild conditions; while if they are biased, then the algorithm would converge with an error floor determined by the accumulated estimate bias over communication rounds. Next, building upon the convergence results, we optimize the power control to directly minimize the derived optimality gaps under the cases without and with unbiased aggregation constraints, subject to a set of average and maximum power constraints at individual edge devices. We transform both problems into convex forms, and obtain their structured optimal solutions, both appearing in a form of regularized channel inversion, by using the Lagrangian duality method. Finally, numerical results show that the proposed power control policies achieve significantly faster convergence for Air-FEEL, as compared with benchmark policies with fixed power transmission or conventional MSE minimization.

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/jsac.2021.3126060

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

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

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 10 references

Research works printed but not linked: 43

  1. 10.1109/ICC42927.2021.9500664 · DOI
  2. 10.1109/MCOM.2019.1900271 · DOI · Paper page
  3. 10.1109/MCOM.001.1900103 · DOI · Paper page
  4. 10.1109/JPROC.2019.2941458 · DOI · Paper page
  5. 10.1109/INFOCOM.2019.8737464 · DOI · Paper page
  6. Konečný, 2016, Federated learning: Strategies for improving communication efficiency, arXiv:1610.05492 · arXiv
  7. 10.1109/JPROC.2021.3055679 · DOI · Paper page
  8. 10.23919/JCIN.2021.9475121 · DOI · Paper page
  9. 10.1109/TWC.2020.3015671 · DOI · Paper page
  10. 10.1109/MWC.011.2000467 · DOI · Paper page
  11. 10.1109/TIT.2008.929967 · DOI · Paper page
  12. 10.1109/INFOCOM.2015.7218555 · DOI · Paper page
  13. 10.1109/TWC.2020.3012287 · DOI · Paper page
  14. 10.1109/TWC.2020.2993703 · DOI · Paper page
  15. 10.1109/TWC.2020.3043787 · DOI
  16. 10.1109/JIOT.2018.2871070 · DOI · Paper page
  17. 10.1109/TCOMM.2021.3051397 · DOI · Paper page
  18. 10.1109/TSP.2020.2970338 · DOI · Paper page
  19. 10.1109/TSP.2020.2989580 · DOI · Paper page
  20. 10.1109/TWC.2019.2946245 · DOI · Paper page
  21. 10.1109/JSAC.2021.3126078 · DOI
  22. 10.1109/ICC42927.2021.9500875 · DOI · Paper page
  23. 10.1109/TWC.2021.3130111 · DOI
  24. Wang, 2021, Edge federated learning via unit-modulus over-the-air computation (extended version), arXiv:2101.12051 · arXiv
  25. 10.1109/TWC.2022.3209190 · DOI
  26. 10.1109/JIOT.2020.3002925 · DOI
  27. 10.1109/JSAC.2021.3118402 · DOI · Paper page
  28. 10.1109/INFOCOM42981.2021.9488818 · DOI
  29. 10.1109/ICCC49849.2020.9238982 · DOI
  30. 10.1109/GLOBECOM42002.2020.9322199 · DOI
  31. Sonee, 2020, Efficient federated learning over multiple access channel with differential privacy constraints, arXiv:2005.07776 · arXiv
  32. 10.1109/ISIT44484.2020.9174426 · DOI · Paper page
  33. 10.1109/MCOM.001.2000744 · DOI
  34. 10.1109/TWC.2021.3065748 · DOI
  35. Hou, 2021, Reducing the communication cost of federated learning through multistage optimization, arXiv:2108.06869 · arXiv
  36. McMahan, Communication-efficient learning of deep networks from decentralized data, 54, 1273
  37. 10.1137/110830629 · DOI · Paper page
  38. Li, 2019, On the convergence of FedAvg on non-IID data, arXiv:1907.02189 · arXiv
  39. 10.1007/978-3-319-46128-1_50 · DOI · Paper page
  40. Bernstein, signSGD: Compressed optimisation for non-convex problems, 80, 560
  41. 10.1137/16M1080173 · DOI · Paper page
  42. 10.1109/TCOMM.2020.2979149 · DOI
  43. 10.1007/springerreference_72235 · doi:10.1007/springerreference_72235

Cited by

See all 173

Metadata

Authors
Cao, X., Zhu, G., Xu, J., Wang, Z., & Cui, S.
Venue
IEEE Journal on Selected Areas in Communications
Published
2022-01
Volume
40
Issue
1
Pages
342-358
ISSN
  • 0733-8716 (ISSN-L)
  • 1558-0008
OpenAlex
W3212347076
Cited by
173
References
10
FWCI
9.88
Type
journal article
Language
en
Open access
green
Funders
  • Special Project for Research and Development in Key areas of Guangdong Province (2018B030338001)
  • National Key Research and Development Program of China (2018YFB1800800)
  • Shenzhen Outstanding Talents Training Fund
  • Guangdong Research Project (2017ZT07X152)
  • National Natural Science Foundation of China (U2001208, 61871137, 62001310)
  • Science and Technology Program of Guangdong Province (2021A0505030002)

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: Optimized Power Control Design for Over-the-Air Federated Edge Learning. https://app.cochat.ai/papers/10.1109/jsac.2021.3126060
The paper
Cao, X., Zhu, G., Xu, J., Wang, Z., & Cui, S. (2022). Optimized Power Control Design for Over-the-Air Federated Edge Learning. IEEE Journal on Selected Areas in Communications. https://doi.org/10.1109/jsac.2021.3126060

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.