Convergence Time Optimization for Federated Learning Over Wireless Networks
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL training loss and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that can select the users who can contribute toward improving the FL convergence speed more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time and the FL training loss. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on the global FL model with high probabilities. Given the user selection po…
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
“A probabilistic device scheduling policy was further proposed in [90], [243] to minimize the overall training time in wireless FL.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [90]
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems
Saad, W., Bennis, M., & Chen, M. (2020) · IEEE Network · doi:10.1109/mnet.001.1900287 · Cited by 4,985 · cited 1×
“However, in wireless networks, it is impractical for wireless users to transmit their training data samples to such a central controller due to privacy concerns and the nature of limited wireless resources [2].”
BackgroundSelf-citationFederated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023 · cited 1×
“distribution [20] or statistical heterogeneity [21].”
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 1×
“The update of the global FL model at iteration µ is given by [23]: where g ( a µ ) is the global FL model at iteration µ , and a µ = [ a 1 ,µ , . . . , a U,µ ] is a user association vector with a i,µ ∈ { 0 , 1 } , a i,µ = 1 indicates that user i connects to the BS and user i must send its local FL…”
BackgroundTowards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334
Adaptive Federated Learning in Resource Constrained Edge Computing Systems
Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904348 · Cited by 2,232 · cited 1×
“The works in [6] and [7] optimized the FL performance with communication constraints such as limited spectrum and computational resources.”
BackgroundFederated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563 · cited 3×
“For comparison purposes, we use two baselines: a) an FL algorithm that uses the proposed user association policy without the prediction of users’ local FL models at each given learning step and b) a standard FL algorithm in [20] that randomly determines user selection and resource allocation without using FNNs to esti…”
MethodA Joint Learning and Communications Framework for Federated Learning over Wireless Networks
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., & Cui, S. (2019) · arXiv · doi:10.48550/arxiv.1909.07972 · Cited by 1,547 · cited 1×
“The works in [6] and [7] optimized the FL performance with communication constraints such as limited spectrum and computational resources.”
BackgroundSelf-citationA Joint Learning and Communications Framework for Federated Learning Over Wireless Networks
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., & Cui, S. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3024629 · Cited by 1,547 · cited 1×
“The works in [6] and [7] optimized the FL performance with communication constraints such as limited spectrum and computational resources.”
BackgroundSelf-citationUser Association for Load Balancing in Heterogeneous Cellular Networks
Ye, Q., Rong, B., Chen, Y., Al-Shalash, M., Caramanis, C., & Andrews, J. G. (2013) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2013.040413.120676 · Cited by 1,228 · cited 2×
“Similarly, the downlink data rate of the BS when transmitting the global FL model parameters to each user i is given by [22]”
BackgroundMethod
Research works printed but not linked: 3
- 2020, Classify MNIST Digits Using a Feedforward Neural Network With MATLAB
- lecun, 2020, The MNIST Database of Handwritten Digits
- 2020, Function Fitting Neural Networks
Cited by
Items 201–300 of 444
Over-the-Air Statistical Estimation
Lee, C.-Z., Barnes, L. P., & Özgür, A. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118412 · Cited by 15
Q-Learning-Aided Offloading Strategy in Edge-Assisted Federated Learning over Industrial IoT
Wu, S., Xue, H., & Zhang, L. (2023) · Electronics · doi:10.3390/electronics12071706 · Cited by 15
A Multi-Perspective Feature Approach to Few-Shot Classification of IoT Traffic
Ma, X., Wang, Y., Lai, Y., Jia, W., Zhao, Z., He, H., Yin, R., & Chen, Y. (2023) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2023.3269842 · Cited by 15
“In this section, we will analyse the convergence of MAFFIT after referring to [36], [37], [38], [39].”
MethodDiversity Maximized Scheduling in RoadSide Units for Traffic Monitoring Applications
Sarlak, A., Razi, A., Chen, X., & Amin, R. (2023) · Conference on Local Computer Networks · doi:10.1109/lcn58197.2023.10223373 · Cited by 15
Performance Optimization of Federated Learning over Mobile Wireless Networks
Chen, M., Poor, H. V., Saad, W., & Cui, S. R. (2020) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc48557.2020.9154300 · Cited by 15
Self-citationMachine Learning for Predictive Deployment of UAVs with Rate Splitting Multiple Access
Lu, L.-Y., Hu, Y., Zhang, Y., Jia, G., Nie, J., & Shikh‐Bahaei, M. (2020) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps50303.2020.9367523 · Cited by 15
Optimization of User Selection and Bandwidth Allocation for Federated Learning in VLC/RF Systems
Liu, C., Guo, C., Yang, Y., Chen, M., Poor, H. V., & Cui, S. R. (2021) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc49053.2021.9417407 · Cited by 15
“These studies include the optimization of energy efficiency and communication cost [3]— [5], framework design and user selection [6]—[11].”
BackgroundSelf-citationA two-stage federated optimization algorithm for privacy computing in Internet of Things
Zhang, J., Ning, Z., & Xue, F. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.03.042 · Cited by 16
Communication-Efficient Federated Learning Over Capacity-Limited Wireless Networks
Yun, J., Oh, Y., Jeon, Y., & Poor, H. V. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3419039 · Cited by 14
“Communication-efficient FL has been extensively investigated for its potential capability for improving the convergence rate of FL under a limited uplink capacity [12], [13], [14], [15].”
Self-citationAsynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients
Sun, Y., Shao, J., Mao, Y., & Zhang, J. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9839045 · Cited by 14
“Prior studies on FEEL were largely restricted to synchronous training, where the client nodes perform the same amount of local training and upload their model updates to an edge server simultaneously for model aggregation [6], [7].”
BackgroundQoS-Aware Resource Bargaining for Federated Learning Over Edge Networks in Industrial IoT
Chakraborty, A., & Misra, S. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3206474 · Cited by 14
“[10] in which the authors used a probabilistic approach to determine the effect of the users local model on the global model and considered the optimal allocation of wireless resource blocks for reducing convergence time and loss.”
MethodDynamic Pricing and Placing for Distributed Machine Learning Jobs: An Online Learning Approach
Zhou, R., Zhang, X., Lui, J. C. S., & Li, Z. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3242707 · Cited by 14
“A a probablistic user selection scheme is studied and proposed in [39], which jointly considers user selection and resource allocation for the minimization of federated learning convergence time while while optimizing the performance.”
MethodWang, T., Huang, N., Wu, Y., & Quek, T. Q. S. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3229277 · Cited by 14
“proposed a probabilistic user selection scheme in [8] that helps the BS select an appropriate set of users to perform FL at each learning step.”
BackgroundMethodInfluentialMajeed, A., & Hwang, S. O. (2024) · IEEE Access · doi:10.1109/access.2024.3413069 · Cited by 14
“7) Optimization: FL systems have been optimized from the perspectives of communication rounds, global and local models, bandwidth allocations, trade-off solutions, model design, network topologies, update sharing and receiving, and convergence time [463], [464].”
BackgroundLocal Loss-Assisted Dynamic Client Selection for Image Classification-Oriented Federated Learning
Ong, S. C., & Gau, R.-H. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838873 · Cited by 14
“Chen et al. [7] studied the convergence time of federated learning over wireless networks.”
BackgroundSaif, M., Hassan, M. Z., & Hossain, M. J. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3410211 · Cited by 13
An efficient federated learning solution for the artificial intelligence of things
Kouda, M. A., Djamaa, B., & Yachir, A. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107533 · Cited by 13
VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning
Ballotta, L., Fabbro, N. D., Perin, G., Schenato, L., Rossi, M., & Piro, G. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3479780 · Cited by 13
“In the present article, these aspects are jointly tackled for the first time, proposing vehicular radio environment map (REM) federated learning (VREM-FL), an FL scheduler that orchestrates the computation and the transmission of local models from the end users (the vehicles) to the central model…”
Fu, Y., Qin, P. D., Tang, G., & Zhao, X. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3559147 · Cited by 13
Random Orthogonalization for Federated Learning in Massive MIMO Systems
Wei, X., Shen, C., Yang, J., & Poor, H. V. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838988 · Cited by 13
“Client scheduling and various power and computation resource allocation methods have been investigated [27]–[32].”
Self-citationYan, Z., Li, D., Zhang, Z., & He, J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3277632 · Cited by 13
Cache-Enabled Federated Learning Systems
Liu, Y., Su, L., Joe‐Wong, C., Ioannidis, S., Yeh, E. M., & Siew, M. (2023) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3565287.3610264 · Cited by 13
On the Optimization of UAV-Assisted Wireless Networks for Hierarchical Federated Learning
Khelf, R., Driouch, E., & Ajib, W. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293857 · Cited by 13
“A probabilistic user selection scheme is proposed in [12] and [13] to prioritize the selection of users that can improve convergence speed and training loss.”
BackgroundZhao, H., Geng, L., Feng, W., & Changming, Z. H. O. U. (2024) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2024.06.023 · Cited by 13
Resource Allocation for Wireless Communications with Distributed Reconfigurable Intelligent Surfaces
Yang, Z., Chen, M., Saad, W., Xu, W., Shikh‐Bahaei, M., Poor, H. V., & Cui, S. R. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322421 · Cited by 13
Self-citationA Decentralized Game Theoretic Approach for Energy-aware Resource Management in Federated Learning
Zaw, C. W., & Hong, C. S. (2021) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp51126.2021.00033 · Cited by 13
“A centralized solution for optimizing the convergence time of the learning algorithm for FL is proposed in [7].”
MethodWang, S., & Zhang, Y. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10060743 · Cited by 13
Reconfigurable Intelligent Surface Empowered Federated Edge Learning With Statistical CSI
Li, H., Wang, R., Wu, J. H., Zhang, W., & Soto, I. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3334250 · Cited by 12
“Besides, as the outage probability decreases, the gap R bias For comparison, we purposefully establish the convergence upper bound over outageless channels with the full gradient descent method [7], [30], [31], on the basis of Theorem 1.”
MethodMulti-frame Scheduling for Federated Learning over Energy-Efficient 6G Wireless Networks
Beitollahi, M., & Lu, N. (2022) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps54753.2022.9798090 · Cited by 12
Latency Minimization for Wireless Federated Learning With Heterogeneous Local Model Updates
Zhu, J., Shi, Y., Fu, M., Zhou, Y., Wu, Y., & Fu, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3285937 · Cited by 12
“Furthermore, Chen et al. [39] showed that the total number of rounds for the FL algorithm to converge depends only on the device selection scheme and has nothing to do with the latency of each communication round, so that they can minimize the convergence time of each iteration.”
BackgroundMethodInfluentialOptimizing Tradeoff Between Learning Speed and Cost for Federated-Learning-Enabled Industrial IoT
Zhang, L., Wu, S., Xu, H., Liu, Q., Hong, C. S., & Han, Z. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3330754 · Cited by 12
“Chen et al. [18] investigated the joint learning, wireless resource allocation, and user selection problem to minimize the FL convergence time.”
BackgroundFRACTAL: Data-Aware Clustering and Communication Optimization for Decentralized Federated Learning
Ma, Q., Liu, J., Xu, H., Jia, Q., & Xie, R. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3403381 · Cited by 12
Novel Visible Light Communication Assisted Perspective-Four-Line Algorithm for Indoor Localization
Bai, L., Yang, Y., Feng, C., Guo, C., & Jia, B. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322127 · Cited by 12
Hyperparameter Free MEEF-Based Learning for Next Generation Communication Systems
Mitra, R., Kaddoum, G., & da Costa, D. B. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3142138 · Cited by 12
Training Time Minimization in Quantized Federated Edge Learning under Bandwidth Constraint
Liu, P., Jiang, J., Zhu, G., Cheng, L., Jiang, W., Luo, W., Du, Y., & Wang, Z. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771723 · Cited by 12
“Training time minimization of AI models is one of the critical concerns in FEEL due to the limited computation and communication resources in edge networks [10].”
BackgroundZhang, S., Yang, Z., Chen, G., Dong, Z., & Han, Z. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3453398 · Cited by 11
“Firstly, despite the data sets are no longer required to send to the central server, but the model training requires a lot of computing resources [5], [6].”
BackgroundGupta, A., & Fernando, X. N. (2025) · Drones · doi:10.3390/drones9070497 · Cited by 11
Integrated Sensing, Communication, and Computing for Cost-effective Multimodal Federated Perception
Chen, N., Cheng, Z., Fan, X., Liu, Z., Huang, B., Zhao, Y., Huang, L., Du, X., & Guizani, M. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3661313 · Cited by 11
Adaptive Idle Model Fusion in Hierarchical Federated Learning for Unbalanced Edge Regions
Xu, J., Fan, H., Wang, Q., Jiang, Y., & Duan, Q. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3410275 · Cited by 11
Reinforcement Learning for Minimizing Age of Information under Realistic Physical Dynamics
Wang, S., Chen, M., Saad, W., Yin, C., Cui, S. R., & Poor, H. V. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322139 · Cited by 11
Self-citationDynamic Task Allocation for Mobile Edge Learning
Mohammad, U., Sorour, S., & Hefeida, M. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3137017 · Cited by 11
RHFedMTL: Resource-Aware Hierarchical Federated Multitask Learning
Yi, X., Li, R., Peng, C., Fei, W., Wu, J., & Zhao, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3392584 · Cited by 10
“Chen et al. [23] proposed a probabilistic user selection scheme to reduce the FL convergence time and the FL training loss.”
BackgroundRamezanlou, M. T., Schwartz, H. M., Lambadaris, I., & Barbeau, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129005 · Cited by 10
Best Effort Voting Power Control for Byzantine-resilient Federated Learning Over the Air
Fan, X., Wang, Y., Huo, Y., & Tian, Z. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814495 · Cited by 10
Zhang, M., Jiang, Y., Zheng, F., Wang, D., Bennis, M., Jamalipour, A., & You, X. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3467285 · Cited by 9
“The F-APs in the edge layer are connected to each other through wired optical cables [39].”
Asynchronous Federated Learning Over Non-IID Data via Over-the-Air Computation
Ma, Q., Song, X., Zhou, J., Wang, H., Liao, Y., Liu, J., & Xu, H. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3641928 · Cited by 9
“However, when deployed at the network edge, FL faces several challenges: 1) Limited communication resource : Traditional orthogonal multiple access (OMA) schemes (TDMA [5], [6], [7], OFDMA [8], [9]) are commonly used for FL model aggregations.”
Optimal and Effective Resource Management in Edge Computing
Majumder, D., & Kumar, S. M. (2022) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.024868 · Cited by 9
Energy-Efficient Classification at the Wireless Edge with Reliability Guarantees
Merluzzi, M., Battiloro, C., Lorenzo, P. D., & Strinati, E. C. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814659 · Cited by 9
GainNet: Coordinates the Odd Couple of Generative AI and 6G Networks
Chen, N., Yang, J., Cheng, Z., Fan, X., Liu, Z., Huang, B., Zhao, Y., Huang, L., Du, X., & Guizani, M. (2024) · IEEE Network · doi:10.1109/mnet.2024.3418671 · Cited by 9
“…resource orchestration mechanisms with 1) minimum latency in communication (ML-C), 2) minimum sum of latency in communication and computing (ML-CC) [12], 3) minimum sum of latency in sensing, communication, and computing (ML-SCC) [13], and 4) maximum product of the number of sensed targets and the…”
BackgroundMeng, Z., Li, Z. Z., Hou, X., Xu, M., Xia, Y., Zhang, Z., & Song, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3521017 · Cited by 9
“Based on the above three assumptions [34], [35], [36], we can calculate the lower bound of the number of local training sessions [37].”
Mobility-Aware Routing and Caching: A Federated Learning Assisted Approach
Cao, Y., Maghsudi, S., & Ohtsuki, T. O. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500804 · Cited by 9
Device Scheduling and Resource Allocation for Federated Learning under Delay and Energy Constraints
Shi, W., Sun, Y., Zhou, S., & Niu, Z. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593178 · Cited by 9
“Among them, the training delay for communication is minimized by device selection and radio resource allocation [8], while computing and communication resource are jointly optimized in [10], [11] to improve energy efficiency.”
BackgroundIntelligent Reflecting Surfaces Enhanced Federated Learning
Ni, W., Liu, Y., & Tian, H. (2020) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps50303.2020.9367578 · Cited by 9
Gupta, A., & Fernando, X. N. (2025) · Drones · doi:10.3390/drones9110771 · Cited by 8
Sun, Y., Kountouris, M., & Zhang, J. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3509852 · Cited by 8
6G Wireless Systems: Challenges and Opportunities
Saad, W. (2020) · Springer eBooks · doi:10.1007/978-3-030-58197-8_7 · Cited by 8
Self-citationWireless Federated Learning over MIMO Networks: Joint Device Scheduling and Beamforming Design
Huang, S., Zhang, P., Mao, Y., Lian, L., Wu, Y., & Shi, Y. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814684 · Cited by 8
“[17] developed a probabilistic device scheduling scheme and first used artificial neural networks for the prediction of model parameters to minimize the convergence time.”
BackgroundMethodDu, H., Chen, Y., Feng, X., Xiang, Q., & Liu, H. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109517 · Cited by 8
Dynamic Network-Assisted D2D-Aided Coded Distributed Learning
Zeulin, N., Galinina, O., Himayat, N., Andreev, S. D., & Heath, R. W. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3259442 · Cited by 8
“Existing methods to reduce the impact of stragglers includes mechanisms, such as coded computing [8], [9], over-the-air computing [10], [11], or specific resource allocation [12], [13], [14] and scheduling [15].”
MethodKnowledge Caching for Federated Learning
Zheng, X., Lee, M., & Hong, Y.-W. P. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685861 · Cited by 8
“[8] considered a similar problem by minimizing the convergence time.”
BackgroundJoint Power Control and Data Size Selection for Over-the-Air Computation-Aided Federated Learning
An, X., Fan, R., Zuo, S., Hu, H., Jiang, H., & Zhang, N. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3341958 · Cited by 7
“The data points collected by all the mobile devices are supposed to follow the same statistical heterogeneity [28].”
BackgroundWang, Q., Xu, S., Xu, R., & Ai, B. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3502444 · Cited by 8
A Novel Hybrid NOMA-TDMA Scheme for Wireless Federated Learning Networks
Xu, D. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3531238 · Cited by 7
Mitigating Evasion Attacks in Federated Learning Based Signal Classifiers
Wang, S., Sahay, R., Piaseczny, A., & Brinton, C. G. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3566954 · Cited by 7
“So, even correctly filtered adversaries can reduce the number of unique signal constellations that a global model is prepared to classify [45], [51], [53].”
Battiloro, C., Merluzzi, M., Lorenzo, P. D., & Barbarossa, S. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746891 · Cited by 7
Efficient Federated Meta‐Learning Over Multi‐Access Wireless Networks
Yue, S., & Ren, J. (2024) · Wiley eBooks · doi:10.1002/9781394180523.ch22 · Cited by 7
Drowsiness Detection Using Federated Learning: Lessons Learnt from Dealing with Non-IID Data
Dautov, R., & Husom, E. J. (2024) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3652037.3652074 · Cited by 7
“…have also examined FL’s performance in terms of fault tolerance and resilience [10, 31], energy efficiency [30, 41], model convergence speed [5, 13, 25], and algorithmic fairness [21, 43]. albeit beyond the scope of this paper, considering all these metrics provide additional insights into…”
BackgroundKarami, F., & Khalaj, B. H. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.107957 · Cited by 7
FedScalar: Federated Learning with Scalar Communication for Bandwidth-Constrained NetworksPreprint
Rostami, M. R., & Kia, S. S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.02260 · Cited by 7
“These solutions focus on optimizing agent scheduling, selection, and network resource management [5], [9]–[14].”
BackgroundBlockchain-Aided Wireless Federated Learning: Resource Allocation and Client Scheduling
Li, J., Zhang, W., Wei, K., Chen, G., Shu, F., Chen, W., & Jin, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3417212 · Cited by 6
“We first introduce some assumptions that are widely used in convergence analysis [36], [37].”
Clipper : Online Joint Client Sampling and Power Allocation for Wireless Federated Learning
Xu, W., Liang, B., Boudreau, G., & Sökün, H. Ü. (2024) · ACM Transactions on Modeling and Performance Evaluation of Computing Systems · doi:10.1145/3703628 · Cited by 6
“A new optimization problem to minimize the convergence time of FL, taking into account wireless communications and at the same time optimizing the performance of FL, was formed and solved in Reference [6].”
Secure Transmission for Intelligent Reflecting Surface Assisted Communication with Deep Learning
Zou, X., Chen, M., Huang, C., Wang, K., & Shikh‐Bahaei, M. (2020) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps50303.2020.9367587 · Cited by 6
Self-citationEnergy Minimization for Federated Learning Based Radio Map Construction
Wu, F., Gao, Y., Xiao, L., Yang, D., & Lyu, J. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3453212 · Cited by 6
FL4SDN: A Fast-Convergent Federated Learning for Distributed and Heterogeneous SDN
Tran, H. A., & Tran, D. (2024) · IEEE Intelligent Systems · doi:10.1109/mis.2024.3453308 · Cited by 6
“Chen et al. 12 implemented FL over a wireless network, where the base station collects and aggregates local models without requiring user data.”
Tynchenko, V. V., Malashin, I. P., Kurashkin, S. O., Tynchenko, V., Gantimurov, A., Nelyub, V., & Бородулин, А. С. (2025) · Future Internet · doi:10.3390/fi17050215 · Cited by 6
Paving the Way for Distributed Artificial Intelligence Over the Air
Ma, G., Zhang, C., Dang, S., & Shihada, B. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3188051 · Cited by 6
Joint Resource Allocation and User Scheduling Scheme for Federated Learning
Shen, J., Cheng, N., Yin, Z., & Xu, W. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625056 · Cited by 6
Stochastic Client Scheduling with Dynamic SINR Thresholds for Fast Federated Learning
Xia, H., Li, Y., Liu, C., & Zhu, Y. (2022) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc55456.2022.9880839 · Cited by 6
“Assuming that OFDMA technology is used in data uploading from clients to the base station [14], the parameter upload delay of client n in round t is given by [15]”
MethodProbabilistic Node Selection for Federated Learning with Heterogeneous Data in Mobile Edge
Wu, H., & Wang, P. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771994 · Cited by 6
“Chen et al. [10] designed a probabilistic model to make node selection where the probability for each node to be selected is proportional to the norm of local gradient.”
Interplay between Distributed AI Workflow and URLLC
Ganjalizadeh, M., Shokri‐Ghadikolaei, H., Haraldson, J., & Petrova, M. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000915 · Cited by 6
“However, using a larger AI model means longer communication and computation time, resulting in higher convergence time [7].”
BackgroundMethodInfluentialUser Assignment and Resource Allocation for Hierarchical Federated Learning over Wireless NetworksPreprint
Zhang, T., Lam, K., & Zhao, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.09253 · Cited by 6
“…method to pursue better learning performance of FL. [29] designs a joint power allocation and scheduling algorithm to optimize the convergence speed of FL. [30] minimizes the time delay for training the entire FL algorithm by introducing a joint resource allocation and user scheduling scheme.”
MethodAdvancing Privacy-Preserving AI: A Survey on Federated Learning and Its ApplicationsPreprint
Nowell, E., & Gallus, S. (2025) · Preprints.org · doi:10.20944/preprints202501.0685.v1 · Cited by 6
Optimal Batch Allocation for Wireless Federated Learning
Song, J., & Jeon, S.-W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3516123 · Cited by 5
“Bandwidth allocation schemes that select users with a probability distribution have also been explored in [13].”
BackgroundJoint Device and Training Scheduling for Wireless Federated Learning
Chen, X., Zhou, X., Zhang, H., Sun, M., & Zhao, T. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3564461 · Cited by 6
“These control variables fall into two categories: 1) device scheduling [6], [7], [10] and 2) training scheduling [11], [12], [13].”
InfluentialFAS-assisted federated learning over wireless communication systems
Xu, H., Wong, K., Zhu, Y., Huang, C., Wang, C., New, W. K., Ghadi, F. R., & Zhou, G. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4433-9 · Cited by 5
Joint Communication and Computation for Federated Learning Over Cell-Free MIMO Network
Wang, Z., Zhang, C., Wang, W., Dai, M., Wang, H., & Huang, Y. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3596953 · Cited by 5
“4 Remark 1: Communication efficiency is often affected by inter-user interference while user selection is a commonly used technique for managing this interference by excluding users with poor channel conditions [20], [22], [23].”
InfluentialSplit Federated Learning for Resource-Constrained Edge Computing Networks
Wang, X., Song, S., Zhang, Z., Hou, X., Li, Z., Xing, T., & Zhang, X.-P. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3626460 · Cited by 5
“The data rate of uplink transmission from the device u to the server is determined by [29] where W denotes the bandwidth allocated to each device u , which is assumed to be equal across all devices.”
Device Scheduling for Wireless Federated Learning with Latency and Representativity
Chen, Z., Yi, W., Deng, Y., & Nallanathan, A. (2022) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme55909.2022.9988590 · Cited by 5
Cost-Effective Federated Learning: A Unified Approach to Device and Training Scheduling
Chen, X., Zhou, X., Zhang, H., Sun, M., & Zhao, T. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622716 · Cited by 6
Efficient algorithm for resource optimization in optical communication networks
Yan, D., Peng, Q., Houichi, M., Alshahrani, R., Abeba, S., & Park, K. (2025) · Optics Express · doi:10.1364/oe.544542 · Cited by 5
Optimizing Federated Learning with Heterogeneous Edge Devices
Islam, M. M., & Alawad, M. (2024) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi60790.2024.10585747 · Cited by 5
“Additionally, adaptive tuning of local training [11], weighting design for model aggregation [14], and node selection strategies [15] [16] aim to achieve better model convergence by considering the varying data characteristics across participating devices.”
BackgroundCommunication-Efficient Federated Learning with Heterogeneous Devices
Chen, Z., Yi, W., Liu, Y., & Nallanathan, A. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279442 · Cited by 5
“Existing works [3], [4] have shown that the FL performance can be improved by scheduling more devices in each round.”
InfluentialMachine Learning over Networks: Co-design of Distributed Optimization and Communications
Mahmoudi, A., Shokri‐Ghadikolaei, H., & Fischione, C. (2020) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc48557.2020.9154264 · Cited by 5
QoS-Constrained Federated Learning Empowered by Intelligent Reflecting Surface
Zheng, J., Ni, W., Tian, H., & Wang, Y. (2021) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc50174.2021.9569612 · Cited by 5
Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling
Zhang, M., Zhu, G., Wang, S., Jiang, J., Zhong, C., & Cui, S. R. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593157 · Cited by 5
Self-citationUser Scheduling in Federated Learning over Energy Harvesting Wireless Networks
Hamdi, R., Chen, M., Said, A. B., Qaraqe, M., & Poor, H. V. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685801 · Cited by 6
“The authors of [6] minimized the convergence time of FL by designing an appropriate user selection scheme.”
MethodSelf-citationContextual Model Aggregation for Fast and Robust Federated Learning in Edge ComputingPreprint
Nguyen, H. T., Poor, H. V., & Chiang, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12738 · Cited by 5
“Other related works include [19], [20], [32] that consider full participation of all devices in every round and also study offloading data to improve convergence speed, [33]– [36] which studies federated learning over wireless networks.”
BackgroundSelf-citationClient Selection for Federated Policy Optimization with Environment HeterogeneityPreprint
Xie, Z., & Song, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.10978 · Cited by 5
Abdellatif, A. A., Mhaisen, N., Mohamed, A., Erbad, A., Guizani, M., Dawy, Z., & Nasreddine, W. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2021.10.016 · Cited by 4
Bidirectional Decoupled Distillation for Heterogeneous Federated Learning
Song, W., Han, L., Yan, M., Li, X., Li, H., & Huang, X. (2024) · Entropy · doi:10.3390/e26090762 · Cited by 4
“The other approaches [29,30] optimize the FL training convergence by utilizing a probabilistic selection scheme.”
Method
Metadata
- Authors
- Chen, M., Poor, H. V., Saad, W., & Cui, S.
- Affiliations
- Princeton University (US)
- Virginia Tech (US)
- Shenzhen Research Institute of Big Data (CN)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2021-04
- Volume
- 20
- Issue
- 4
- Pages
- 2457-2471
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W3111182214
- Cited by
- 403
- References
- 28
- Citations by year
- 2026: 28 · 2025: 50 · 2024: 80 · 2023: 69 · 2022: 71 · 2021: 71
- FWCI
- 24.08
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2018YFB1800800)
- Key Area R&D Program of Guangdong Province (2018B030338001)
- Shenzhen Outstanding Talents Training Fund
- Guangdong Research Project (2017ZT07X152)
- U.S. National Science Foundation (CCF-1908308, CCF-0939370, CCF-1513915)
- Office of Naval Research (N00014-19-1-2621)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- federated learning, convergence time, wireless networks, user selection, uplink resource allocation, resource blocks, artificial neural networks, training loss, base station, handwritten digit recognition
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.