Collaborative Machine Learning at the Wireless Edge with Blind Transmitters
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We study wireless collaborative machine learning (ML), where mobile edge devices, each with its own dataset, carry out distributed stochastic gradient descent (DSGD) over-the-air with the help of a wireless access point acting as the parameter server (PS). At each iteration of the DSGD algorithm wireless devices compute gradient estimates with their local datasets, and send them to the PS over a wireless fading multiple access channel (MAC). Motivated by the additive nature of the wireless MAC, we propose an analog DSGD scheme, in which the devices transmit scaled versions of their gradient estimates in an uncoded fashion. We assume that the channel state information (CSI) is available only at the PS. We instead allow the PS to employ multiple antennas to alleviate the destructive fading effect, which cannot be cancelled by the transmitters due to the lack of CSI. Theoretical analysis indicates that, with the proposed DSGD scheme, increasing the number of PS antennas mitigates the fading effect, and, in the limit, the effects of fading and noise disappear, and the PS receives aligned signals used to update the model parameter. The theoretical results are then corroborated with the experimental ones.
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.
Integrity signals
Registry
Cites
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.
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
Deep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · arXiv · doi:10.48550/arxiv.1502.02551 · Cited by 1,364 · cited 1×
“We note that with SGD the empirical variances of the gradient estimates decay over time and approach zero asymptotically [3], [4], [6], [13], [14].”
BackgroundFederated Learning via Over-the-Air Computation
Yang, K., Jiang, T., Shi, Y., & Ding, Z. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2961673 · Cited by 1,084 · cited 1×
“A single-input multiple-output (SIMO) wireless fading MAC is studied in [8], where a beamforming technique is designed to maximize the number of devices participating in each iteration, while keeping the quality of the received signal at the PS above the specified threshold level.”
MethodMachine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
Mohammadi Amiri, M., & Gunduz, D. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2981904 · Cited by 548
Research works printed but not linked: 11
- Alistarh, QSGD: Communication-efficient SGD via randomized quantization and encoding, 1709
- 10.21437/interspeech.2014-274 · DOI · Paper page
- 10.21437/interspeech.2015-354 · DOI · Paper page
- 10.1109/TSP.2019.2952051 · DOI · Paper page
- 10.1109/ISIT.2019.8849334 · DOI · Paper page
- 10.1109/ICC.2019.8761429 · DOI
- 10.1109/SPAWC.2019.8815402 · DOI · Paper page
- 10.1109/TWC.2020.2974748 · DOI · Paper page
- 10.1109/WCL.2014.022314.140005 · DOI · Paper page
- 10.1109/MSP.2011.2178495 · DOI · Paper page
- 10.1007/978-3-7908-2604-3_16 · DOI · Paper page
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“3) Stochastic Optimization: In large-scale edge AI systems, the estimated CSI will be inevitably imperfect or partially available [271], [177].”
BackgroundMachine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
Mohammadi Amiri, M., & Gunduz, D. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2981904 · Cited by 548
“The digital and analog approaches proposed in this paper can be extended to more complicated channel models as it has been done in the follow up works [34]–[37].”
MethodDistributed Learning in Wireless Networks: Recent Progress and Future Challenges
Chen, M., Gunduz, D., Huang, K., Saad, W., Bennis, M., Feljan, A. V., & Poor, H. V. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118346 · Cited by 548
Self-citationHierarchical Federated Learning ACROSS Heterogeneous Cellular Networks
Abad, M. S. H., Ozfatura, E., GUndUz, D., & Ercetin, O. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054634 · Cited by 424
Zhu, G., Du, Y., Gunduz, D., & Huang, K. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3039309 · Cited by 376
“Subsequently, channel-state information (CSI) requirement for overthe-air aggregation is relaxed by exploiting multiple antennas at the edge server in [18].”
Background
Metadata
- Authors
- Amiri, M. M., Duman, T. M., & Gunduz, D.
- Venue
- 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 1-5
- ISSN
- 2376-4066 (ISSN-L)
- OpenAlex
- W2959989160
- Cited by
- 58
- References
- 3
- FWCI
- 4.81
- Type
- conference paper
- Language
- en
- Open access
- green
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: Collaborative Machine Learning at the Wireless Edge with Blind Transmitters. https://app.cochat.ai/papers/10.1109/globalsip45357.2019.8969185
- The paper
- Amiri, M. M., Duman, T. M., & Gunduz, D. (2019). Collaborative Machine Learning at the Wireless Edge with Blind Transmitters. 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP). https://doi.org/10.1109/globalsip45357.2019.8969185
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.