Optimal Adaptive Power Control for Over-The-Air Federated Edge Learning Under Fading Channels
Abstract
Channel fading can have a strong impact on the convergence of over-the-air federated edge learning (OTA-FEEL). This paper develops a new and optimal power control policy to minimize the optimality gap of OTA-FEEL under any independently and identically distributed fading. Specifically, we reveal that the optimal power control policy takes a structure where the variance of the effective channel from a device to the server should be minimized when its mean is given. Following this structure, a novel nested optimization algorithm is developed to iteratively minimize the variance using the Lagrange-dual method and then optimize the mean of the effective channel using one-dimensional search. A quasi-closed-form expression of the optimal power control policy is derived. It is shown that the optimal adaptive power control for OTA-FEEL performs an integration of the “channel inverting” strategy and the opposite “channel-proportional” strategy to balance the mean and variance of the effective channel. We also generalize the new policy when the channel statistics are unknown a-priori, and show that the optimal policy can be asymptotically approached over time. Simulations confirm the superiority of the policy to its existing alternatives in the convergence speed and learning accuracy of OTA-FEEL.
Integrity signals
Registry
Cites
Statistics
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?
The emerging OTA-WFL may pose new challenges to existing aggregation-phase defenses because the FL server only accesses the aggregated global model, obscuring local models and allowing backdoor attacks to take place unnoticed.
“the emerging OTA-WFL may pose new challenges to the existing defense mechanisms designed for the aggregation phase due to the fact that the FL server would only access the aggregated global model under OTA-WFL [14], [101]. The local models of individual clients are obscured. While this helps improve the privacy of the individuals' local models to a great extent, it allows backdoor attacks to take”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [101]
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601 · see citing works
Bertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 11,969 · see citing works
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937 · see citing works
Convex Optimization: Algorithms and Complexity
Bubeck, S. (2015) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000050 · Cited by 1,273 · see citing works
Federated 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× · see citing works
“In [11], user selection and beamforming were jointly optimized for OTA global model aggregations.”
MethodBroadband Analog Aggregation for Low-Latency Federated Edge Learning
Zhu, G., Wang, Y., & Huang, K. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2946245 · Cited by 786 · see citing works
Machine 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 · see citing works
Maximizing Queueing Network Utility Subject to Stability: Greedy Primal-Dual Algorithm
Stolyar, A. (2005) · Queueing Systems · doi:10.1007/s11134-005-1450-0 · Cited by 532 · see citing works
Robust Truncated Hinge Loss Support Vector Machines
Wu, Y., & Liu, Y. (2007) · Journal of the American Statistical Association · doi:10.1198/016214507000000617 · Cited by 378 · see citing works
Adaptive signal processing algorithms: stability and performance
Solo, V., & Kong, X. (1994) · Prentice-Hall, Inc eBooks · Cited by 300 · see citing works
Over-the-Air Federated Learning From Heterogeneous Data
Sery, T., Shlezinger, N., Cohen, K., & Eldar, Y. C. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3090323 · Cited by 247 · see citing works
Over-the-Air Computing for Wireless Data Aggregation in Massive IoT
Zhu, G., Xu, J., Huang, K., & Cui, S. R. (2021) · IEEE Wireless Communications · doi:10.1109/mwc.011.2000467 · Cited by 236 · see citing works
Privacy for Free: Wireless Federated Learning via Uncoded Transmission With Adaptive Power Control
Liu, D., & Simeone, O. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036948 · Cited by 234 · see citing works
Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
Qu, L., Zhou, Y., Liang, P. P., Xia, Y., Wang, F., Adeli, E., Fei-Fei, L., & Rubin, D. L. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00982 · Cited by 220 · see citing works
Convex Optimization for Signal Processing and Communications
Chi, C., Li, W.-C., & Lin, C.-H. (2017) · CRC Press eBooks · doi:10.1201/9781315366920 · Cited by 203 · see citing works
A Unified Approach to QoS-Guaranteed Scheduling for Channel-Adaptive Wireless Networks
Wang, X., Giannakis, G. B., & Marques, A. G. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2007.907120 · Cited by 195 · see citing works
Self-citationOptimized Power Control Design for Over-the-Air Federated Edge Learning
Cao, X., Zhu, G., Xu, J., Wang, Z., & Cui, S. R. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126060 · Cited by 176 · see citing works
The million song dataset challenge
McFee, B., Bertin-Mahieux, T., Ellis, D. P. W., et al. (2012) · International World Wide Web Conference (WWW) · doi:10.1145/2187980.2188222 · Cited by 174 · see citing works
On Analog Gradient Descent Learning Over Multiple Access Fading Channels
Sery, T., & Cohen, K. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2989580 · Cited by 172 · see citing works
Gradient Statistics Aware Power Control for Over-the-Air Federated Learning
Zhang, N., & Tao, M. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3065748 · Cited by 153 · see citing works
Strong convexity of sets and functions
Vial, J.-P. (1982) · Journal of Mathematical Economics · doi:10.1016/0304-4068(82)90026-x · Cited by 146 · see citing works
Resource Allocation for Wireless Multiuser OFDM Networks
Wang, X., & Giannakis, G. B. (2011) · IEEE Transactions on Information Theory · doi:10.1109/tit.2011.2145770 · Cited by 134 · see citing works
Self-citationTransmission Power Control for Over-the-Air Federated Averaging at Network Edge
Cao, X., Zhu, G., Xu, J., & Cui, S. R. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3143217 · Cited by 115 · see citing works
Joint Optimization of Communications and Federated Learning Over the Air
Fan, X., Wang, Y., Huo, Y., & Tian, Z. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3130111 · Cited by 74 · see citing works
Large-Margin Regularized Softmax Cross-Entropy Loss
Li, X., Chang, D., Tian, T., & Cao, J. (2019) · IEEE Access · doi:10.1109/access.2019.2897692 · Cited by 51 · see citing works
Distributed Learning for Low Latency Machine Type Communication in a Massive Internet of Things
Park, T., & Saad, W. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2903832 · Cited by 50 · see citing works
Federated Learning via Over-the-Air Computation With Statistical Channel State Information
Jing, S., & Xiao, C. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3175887 · Cited by 46 · see citing works
Federated Learning Over Wireless Channels: Dynamic Resource Allocation and Task Scheduling
Chu, S., Li, J., Wang, J., Wang, Z., Ding, M., Zhang, Y.-J., Qian, Y., & Chen, W. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3196009 · Cited by 35 · see citing works
Su, L., & Lau, V. K. N. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3096570 · Cited by 32 · see citing works
Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
Yang, H., Qiu, P., Jia, L., & Yener, A. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834342 · Cited by 29 · see citing works
Over-the-Air Federated Learning with Retransmissions
Hellström, H., Fodor, V., & Fischione, C. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593119 · Cited by 23 · see citing works
Parameter Estimation for a Regression Model
Härdle, W. K., Spokoiny, V. G., Panov, V., et al. (2013) · Springer texts in statistics · doi:10.1007/978-3-642-36850-9_3 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Wan, Y., Qu, Y., Ni, W., Xiang, Y., Gao, L., & Hossain, E. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3361451 · Cited by 152 · see citing works
“Inaddition to the above-mentioned limitations, the emerging OTA-WFL may pose new challenges to the existing defense mechanisms designed for the aggregation phase due to the fact that the FL server would only access the aggregated global model under OTA-WFL [14], [101].”
BackgroundMethodSelf-citation
- Authors
- Yu, X., Xiao, B., Ni, W., & Wang, X.
- Affiliations
- Fudan University (CN)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Venue
- IEEE Transactions on Communications
- Published
- 2023-09
- Volume
- 71
- Issue
- 9
- Pages
- 5199-5213
- ISSN
- 0090-6778 (ISSN-L)
- 1558-0857
- OpenAlex
- W4379622636
- Cited by
- 19
- References
- 33
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 4
- FWCI
- 1.79
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Communications (publishedVersion)
- Funders
- Innovation Program of Shanghai Municipal Science and Technology Commission (20JC1416400, 21XD1400300)
- National Natural Science Foundation of China (62231010, 62071126)
- 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 › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Keywords
- adaptive power control, fading channels, optimality gap, nested optimization, Lagrange dual method, unknown channel statistics, convergence rate
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
