The DOI matches its Crossref record; 62 of the 66 references it cites were found in a registry or an index.
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
Open accessAbstract
We study federated machine learning (ML) at the wireless edge, where power- and bandwidth-limited wireless devices with local datasets carry out distributed stochastic gradient descent (DSGD) with the help of a parameter server (PS). Standard approaches assume separate computation and communication, where local gradient estimates are compressed and transmitted to the PS over orthogonal links. Following this digital approach, we introduce D-DSGD, in which the wireless devices employ gradient quantization and error accumulation, and transmit their gradient estimates to the PS over a multiple access channel (MAC). We then introduce a novel analog scheme, called A-DSGD, which exploits the additive nature of the wireless MAC for over-the-air gradient computation, and provide convergence analysis for this approach. In A-DSGD, the devices first sparsify their gradient estimates, and then project them to a lower dimensional space imposed by the available channel bandwidth. These projections are sent directly over the MAC without employing any digital code. Numerical results show that A-DSGD converges faster than D-DSGD thanks to its more efficient use of the limited bandwidth and the natural alignment of the gradient estimates over the channel. The improvement is particularly compelling at low power and low bandwidth regimes. We also illustrate for a classification problem that, A-DSGD is more robust to bias in data distribution across devices, while D-DSGD significantly outperforms other digital schemes in the literature. We also observe that both D-DSGD and A-DSGD perform better with the number of devices, showing their ability in harnessing the computation power of edge devices.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Specifically, for edge training systems via AirComp, the global model aggregation errors due to the wireless channel fading and noise will cause learning performance degradation [45], [87].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [45]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We run experiments on the MNIST dataset [45] with N = 60000 training and 10000 test data samples, and train a single layer neural network with d = 7850 parameters utilizing ADAM optimizer [46].”
MethodCommunication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 1×
“Our work can easily be combined with the federated averaging algorithm in [6], where multiple SGD iterations are carried out locally before forwarding the models differences to the PS.”
MethodAn Introduction to the Theory of Statistics
(1911) · Nature · doi:10.1038/087345a0 · Cited by 4,394
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766 · cited 3×
“In the FL framework [5]–[7], devices collaboratively learn a model with the help of a PS.”
BackgroundMessage-passing algorithms for compressed sensing
Donoho, D. L., Maleki, A., & Montanari, A. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0909892106 · Cited by 2,416 · cited 1×
“We use approximate message passing (AMP) algorithm to do this at the PS [31].”
MethodAccelerating Stochastic Gradient Descent using Predictive Variance Reduction
Johnson, R., & Zhang, T. (2013) · Cited by 1,889
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761315 · Cited by 1,875
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2018) · arXiv · doi:10.48550/arxiv.1804.08333 · Cited by 1,875
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., & Zou, Y. (2016) · arXiv · doi:10.48550/arxiv.1606.06160 · Cited by 1,690
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
Federated Multi-Task LearningPreprint
Smith, V., Chiang, C.-K., Sanjabi, M., & Talwalkar, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10467 · Cited by 1,320
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Lin, Y., Han, S., Mao, H., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1712.01887 · Cited by 1,134 · cited 2×
“Sparsification reduces the communication time by sending only some values of the gradient vectors [3], [19]–[24], and can be considered as another way of lossy compression, but it is assumed that the chosen entries of the gradient vectors are transmitted reliably, e.”
BackgroundMethodFederated 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 3×
“We also remark that both [32] and [33] consider transmitting model updates, while we focus on gradient transmission, which is more energyefficient as each device transmits only the innovation obtained through gradient descent at that particular iteration (together with error accumulation), whereas model transmission w…”
BackgroundQSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
Alistarh, D., Grubic, D., Li, J., Tomioka, R., & Vojnović, M. (2016) · London School of Economics and Political Science Research Online (London School of Economics and Political Science) · doi:10.48550/arxiv.1610.02132 · Cited by 859
Speeding Up Distributed Machine Learning Using Codes
Lee, K., Lam, M., Pedarsani, R., Papailiopoulos, D., & Ramchandran, K. (2018) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2736066 · Cited by 829 · cited 1×
“kers, by jointly designing the distribution of the data samples across the workers, pre-processing of the computed gradients at the workers, and post-processing of the received computations by the PS [5]–[10]. Thus, the PS does not need to wait for the computations from all the workers to update the global parameter v…”
MethodThe Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
Bayati, M., & Montanari, A. (2011) · IEEE Transactions on Information Theory · doi:10.1109/tit.2010.2094817 · Cited by 780
Introduction to The Theory of Statistics.
Theobald, C. M., & Larson, H. J. (1974) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2345153 · Cited by 762
Broadband Analog Aggregation for Low-Latency Federated Edge Learning
Zhu, G., Wang, Y., & Huang, K. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2946245 · Cited by 761 · cited 3×
“We also remark that both [32] and [33] consider transmitting model updates, while we focus on gradient transmission, which is more energy-efficient as each device transmits only the innovation obtained through gradient descent at that particular iteration (together with error accumulation), whereas model transmission…”
BackgroundFederated Learning Over Wireless Fading Channels
Amiri, M. M., & Gunduz, D. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2974748 · Cited by 625 · cited 2×
“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].”
MethodSelf-citationTernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Wen, W., Xu, C., Yan, F., Wu, C., Wang, Y., Chen, Y., & Li, H. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07878 · Cited by 622 · cited 1×
“Quantization methods implement lossy compression of the gradient vectors by quantizing each of their entries to a finite-bit low precision value [2], [4], [13]–[18].”
MethodSparse Communication for Distributed Gradient Descent
Aji, A. F., & Heafield, K. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1045 · Cited by 585
Federated Optimization:Distributed Optimization Beyond the Datacenter
Konečný, J., McMahan, B., & Ramage, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03575 · Cited by 544
signSGD: Compressed Optimisation for Non-Convex Problems
Bernstein, J., Wang, Y.-X., Azizzadenesheli, K., & Anandkumar, A. (2018) · arXiv · doi:10.48550/arxiv.1802.04434 · Cited by 541 · cited 12×
“Numerical results show that the proposed analog scheme A-DSGD has a better convergence behaviour compared to its digital counterpart, while D-DSGD outperforms the digital schemes studied in [2], [16].”
MethodResultInfluentialThe Convergence of Sparsified Gradient MethodsPreprint
Alistarh, D., Hoefler, T., Johansson, M., Khirirat, S., Konstantinov, N., & Renggli, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10505 · Cited by 523 · cited 1×
“We establish the convergence using rate supermartingale stochastic processes (refer to [23], [44] for a detailed definition of the supermartingale and rate supermartingale processes).”
MethodScalable distributed DNN training using commodity GPU cloud computing
Strom, N. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-354 · Cited by 521 · cited 1×
“Sparsification reduces the communication time by sending only some values of the gradient vectors [3], [19]–[24], and can be considered as another way of lossy compression, but it is assumed that the chosen entries of the gradient vectors are transmitted reliably, e.g., at a very high resolution.”
BackgroundLimit of the Smallest Eigenvalue of a Large Dimensional Sample Covariance Matrix
Bai, Z. D., & Yin, Y. Q. (1993) · The Annals of Probability · doi:10.1214/aop/1176989118 · Cited by 519
Federated Learning: Collaborative Machine Learning without Centralized Training Data
A, A. V., Binny, S., R, J. T., Raj, N., & Thomas, V. (2022) · international journal of engineering technology and management sciences · doi:10.46647/ijetms.2022.v06i05.052 · Cited by 489 · cited 1×
“In the FL framework [5]–[7], devices collaboratively learn a model with the help of a PS.”
BackgroundDistributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2956472 · Cited by 459 · cited 2×
“Another approach is to reduce the frequency of communication from the devices by allowing local parameter updates [5]–[12], [25], [26].”
BackgroundSeide, F., Fu, H., Droppo, J., Li, G., & Yu, D. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-274 · Cited by 443 · cited 3×
“While the communication bottleneck in DSGD has been widely acknowledged in the literature [2]–[4], ML literature ignores the characteristics of the communication channel, and simply focus on reducing the amount of data transmitted from each device to the PS.”
BackgroundMethodGradient Coding: Avoiding Stragglers in Distributed Learning
Tandon, R., Lei, Q., Dimakis, A. G., & Karampatziakis, N. (2017) · International Conference on Machine Learning · Cited by 431
Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication
Sattler, F., Wiedemann, S., Muller, K.-R., & Samek, W. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852172 · Cited by 240 · cited 4×
“For gradient compression, we will consider stateof-the-art quantization approaches together with local error accumulation [21].”
BackgroundMethodInfluentialDon't Use Large Mini-Batches, Use Local SGD
Lin, T., Stich, S. U., Patel, K. K., & Jaggi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.07217 · Cited by 193 · cited 1×
“Another approach is to reduce the frequency of communication from the devices by allowing local parameter updates [5]–[12], [25], [26].”
BackgroundLocal SGD Converges Fast and Communicates Little
Stich, S. U. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09767 · Cited by 191 · cited 1×
“Another approach is to reduce the frequency of communication from the devices by allowing local parameter updates [5]–[12], [25], [26].”
BackgroundATOMO: Communication-efficient Learning via Atomic Sparsification
Wang, H., Sievert, S., Charles, Z., Liu, S., Wright, S. J., & Papailiopoulos, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.04090 · Cited by 189
Robust Analog Function Computation via Wireless Multiple-Access Channels
Goldenbaum, M., & Stanczak, S. (2013) · IEEE Transactions on Communications · doi:10.1109/tcomm.2013.072913.120815 · Cited by 187 · cited 2×
“It is known that separation-based approaches to distributed compression and computing over wireless channels are suboptimal in general [27], [28].”
BackgroundTaming the Wild: A Unified Analysis of Hogwild!-Style Algorithms
De, C., Zhang, C., Olukotun, K., & Ré, C. (2015) · PubMed · doi:10.48550/arxiv.1506.06438 · Cited by 176 · cited 3×
“Next we present a rate supermartingale process for the stochastic process with the update in (4), introduced in [44].”
BackgroundMethodImproving Distributed Gradient Descent Using Reed-Solomon Codes
Halbawi, W., Azizan, N., Salehi, F., & Hassibi, B. (2018) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2018.8437467 · Cited by 169
Error Compensated Quantized SGD and its Applications to Large-scale Distributed OptimizationPreprint
Wu, J., Huang, W., Huang, J., & Zhang, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.08054 · Cited by 162
SparCML: high-performance sparse communication for machine learning
Renggli, C., Ashkboos, S., Aghagolzadeh, M., Alistarh, D., & Hoefler, T. (2019) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3295500.3356222 · Cited by 128
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced OverfittingPreprint
Sun, X., Ren, X., Ma, S., & Wang, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.06197 · Cited by 126
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGDPreprint
Dutta, S., Joshi, G., Ghosh, S., Dube, P., & Nagpurkar, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.01113 · Cited by 125
Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data
Ahn, J.-H., Simeone, O., & Kang, J. (2019) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2019.8904164 · Cited by 125
Capacity-Achieving Sparse Superposition Codes via Approximate Message Passing Decoding
Rush, C., Greig, A., & Venkataramanan, R. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2649460 · Cited by 119
Rateless Codes for Near-Perfect Load Balancing in Distributed Matrix-Vector Multiplication
Mallick, A., Chaudhari, M., Sheth, U., Palanikumar, G., & Joshi, G. (2019) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3366706 · Cited by 115
Exploitation of Stragglers in Coded Computation
Kiani, S., Ferdinand, N. S., & Draper, S. C. (2018) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2018.8437871 · Cited by 114
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
Amiri, M. M., & Gündüz, D. (2019) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2019.8849334 · Cited by 114 · cited 1×
“We propose an alternative analog communication approach, in which the devices transmit their local gradient estimates directly over the wireless channel, extending our previous work in [29].”
MethodNear-Optimal Straggler Mitigation for Distributed Gradient Methods
Li, S.-Z., Kalan, S. M. M., Avestimehr, A., & Soltanolkotabi, M. (2017) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2018.00137 · Cited by 105
Wireless Network Intelligence at the Edge
Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2941458 · Cited by 92 · cited 1×
“Therefore, a much more desirable and practically viable alternative is to develop collaborative ML techniques, also known as federated learning (FL), that can exploit the local datasets and processing capabilities of edge devices, requiring limited communications (see [1] for a survey of applications of edge intellige…”
BackgroundThe dynamics of message passing on dense graphs, with applications to compressed sensing
Bayati, M., & Andrea Montanari, A. (2010) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2010.5513529 · Cited by 92 · cited 1×
“Accordingly, the model parameter vector in Algorithm 1 is updated as follows: Lemma 1: [40]–[42] Consider reconstructing vector x ∈ R d with sparsity level k and (cid:4) x 2 = P from a noisy observation y = A s x + z , where A s ∈ R s × d is the measurement matrix, and z ∈ R s is the noise vector…”
MethodHierarchical Coded Computation
Ferdinand, N. S., & Draper, S. C. (2018) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2018.8437473 · Cited by 85
Source and Channel Coding for Correlated Sources Over Multiuser Channels
Gündüz, D., Erkip, E., Goldsmith, A. J., & Poor, H. V. (2009) · IEEE Transactions on Information Theory · doi:10.1109/tit.2009.2025566 · Cited by 85 · cited 1×
“It is known that separation-based approaches to distributed compression and computing over wireless channels are suboptimal in general [27], [28].”
BackgroundVariance-based Gradient Compression for Efficient Distributed Deep LearningPreprint
Tsuzuku, Y., Imachi, H., & Akiba, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06058 · Cited by 76 · cited 1×
“Sparsification reduces the communication time by sending only some values of the gradient vectors [3], [19]–[24], and can be considered as another way of lossy compression, but it is assumed that the chosen entries of the gradient vectors are transmitted reliably, e.”
BackgroundRandomized distributed mean estimation: Accuracy vs. communication
Konečný, J., & Richtárik, P. (2018) · Frontiers in Applied Mathematics and Statistics · doi:10.3389/fams.2018.00062 · Cited by 69
Over-the-Air Machine Learning at the Wireless Edge
Amiri, M. M., & Gündüz, D. (2019) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2019.8815402 · Cited by 58
Collaborative Machine Learning at the Wireless Edge with Blind Transmitters
Amiri, M. M., Duman, T. M., & Gündüz, D. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.8969185 · Cited by 58 · cited 1×
“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].”
MethodComputation Scheduling for Distributed Machine Learning with Straggling Workers
Amiri, M. M., & Gündüz, D. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682911 · Cited by 51
SparCML: High-Performance Sparse Communication for Machine LearningPreprint
Renggli, C., Ashkboos, S., Aghagolzadeh, M., Alistarh, D., & Hoefler, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08021 · Cited by 31
Robust Gradient Descent via Moment Encoding with LDPC CodesPreprint
Maity, R. K., Rawat, A. S., & Mazumdar, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08327 · Cited by 30
SparseCast: Hybrid Digital-Analog Wireless Image Transmission Exploiting Frequency-Domain Sparsity
Tung, T.-Y., & Gündüz, D. (2018) · IEEE Communications Letters · doi:10.1109/lcomm.2018.2877316 · Cited by 25 · cited 2×
“A similar idea is recently used in [30] for analog image transmission over a bandwidth-limited channel.”
BackgroundMethodThe Error Probability of Sparse Superposition Codes With Approximate Message Passing Decoding
Rush, C., & Venkataramanan, R. (2018) · IEEE Transactions on Information Theory · doi:10.1109/tit.2018.2882177 · Cited by 22 · cited 1×
“Accordingly, the model parameter vector in Algorithm 1 is updated as follows: Lemma 1: [40]–[42] Consider reconstructing vector x ∈ R d with sparsity level k and (cid:4) x 2 = P from a noisy observation y = A s x + z , where A s ∈ R s × d is the measurement matrix, and z ∈ R s is the noise vector…”
MethodRunning sparse and low-precision neural network: When algorithm meets hardware
Li, B., Wen, W., Mao, J., Li, S., Chen, Y., & Li, H. (2018) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1109/aspdac.2018.8297378 · Cited by 18 · cited 1×
“Quantization methods implement lossy compression of the gradient vectors by quantizing each of their entries to a finite-bit low precision value [2], [4], [13]–[18].”
MethodRunning sparse and low-precision neural network: when algorithm meets hardware
Li, B., Wen, W., Mao, J., Li, S., Chen, Y., & Li, H. H. (2018) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.5555/3201607.3201733 · Cited by 8
Research works printed but not linked: 1
- strom, 0, Scalable distributed DNN training using commodity GPU cloud computing, Proc INTERSPEECH, 1488
Cited by
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
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
Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications
Gunduz, D., Qin, Z., Aguerri, I. E., Dhillon, H. S., Yang, Z., Yener, A., Wong, K. K., & Chae, C.-B. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3223408 · Cited by 776
Federated Learning Over Wireless Fading Channels
Amiri, M. M., & Gunduz, D. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2974748 · Cited by 625
Self-citationDistributed 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
Metadata
- Authors
- Mohammadi Amiri, M., & Gunduz, D.
- Venue
- IEEE Transactions on Signal Processing
- Published
- 2020
- Volume
- 68
- Pages
- 2155-2169
- ISSN
- 1053-587X (ISSN-L)
- 1941-0476
- OpenAlex
- W2907379776
- Cited by
- 548
- References
- 66
- Citations by year
- 2026: 29 · 2025: 62 · 2024: 67 · 2023: 82 · 2022: 117 · 2021: 123 · 2020: 54
- FWCI
- 36.93
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- Spiral (Imperial College London) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Research Council
- BEACON (677854)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- federated learning, wireless edge computing, distributed stochastic gradient descent, over-the-air computation, multiple access channel, gradient quantization, gradient sparsification, parameter server, low-power communication, convergence analysis, non-IID data
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
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.