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 401–444 of 444
Kherani, N. A. (2025) · National Conference on Communications · doi:10.1109/ncc63735.2025.10983036
Resource Optimization and Hyperparameter Tuning in Decentralized Federated Learning via MPC
Karami, F., & Khalaj, B. H. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11100387
“Similarly, [4] enhances FL performance with user selection schemes, while [5] jointly optimizes user selection and network parameters, considering packet error rates.”
Zheng, Z., & Du, J. (2025) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn65249.2025.11133765
“The transmission rate of client i is given by [13]: the formula (4) is based on Shannon’s theorem and i = [ i 1 , . . . , (cid:2) ij , . . . , (cid:2) iR ] is an RB allocation vector with (cid:2) ij ∈ { 0 , 1 } .”
Federated Edge Learning via Unmanned Aerial Vehicle
Zhou, Y., Fang, W., Shi, Y., & Letaief, K. B. (2025) · Wireless networks · doi:10.1007/978-3-031-96649-1_6
Trustworthy Federated Edge Learning via Blockchain
Zhou, Y., Fang, W., Shi, Y., & Letaief, K. B. (2025) · Wireless networks · doi:10.1007/978-3-031-96649-1_9
A Joint Decoding Scheme for Communication-Efficient NOMA-Empowered Federated Learning
Chen, J., Cai, S., Wan, H., & Ma, X. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3612733
“…: Due to wireless/computation resource constraints, there have also been efforts in developing resource allocation and device selection strategies to minimize the loss [15], [48], to reduce energy consumption [5], [49], [50], [51] and to accelerate the training process [21], [52], [53], [54], [55].”
FL-Swarm MRCM: A Novel Federated Learning Framework for Cross-Site Medical Image Reconstruction
Izhar, A., & Anwar, S. M. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9110295
“There are several implementation strategies for federated learning including FedAvg [2], FedProx [19], FedSGD [20], and FedDyn [21].”
Bhande, A. S. (2025) · EPJ Web of Conferences · doi:10.1051/epjconf/202534101024
FedCB: Joint Client Selection and Bandwidth Allocation for Unreliable Aerial Federated Learning
Li, M., Wu, T., Shen, Z., Wang, H., Huang, Y., & Liu, H. (2025) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290381
Li, Y. (2023) · ANU Open Research (Australian National University) · doi:10.25911/kfnt-0p96
Hossen, N. (2024) · HARVEST (University of Saskatchewan)
Heterogeneous Federated Learning Frameworks for Balancing Job Completion Time and Model Accuracy
Wang, R., Zhou, R., Yu, J., Li, B., & Li, Y. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3603254
“To start with, we need to properly select three critical control parameters including the total number of training rounds, the number of iterations and the number of participating clients in each round [7], [9], [10].”
Robust and Efficient Cross-silo Blockchained Federated Learning with Proof of Generalization
Ren, P., & Yan, T. (2025) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci67886.2025.11308176
“BFL latency has been studied through system parameter optimization [2-3] and learning settings [13-14], Kim et al. [2] reduced end-to-end delay via block generation rates, while Nguyen et al. [3] optimized transmission power and bandwidth using deep reinforcement learning.”
Chen, J.-J., & Liu, K.-H. S. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11310519
“Consequently, our approach eliminates the need for bandwidth allocation variables, as considered in [5], [6], and avoids the assumption of arbitrary bandwidth allocation ratios, as required in [4], [6].”
He, Y., Meng, D., Zhou, H., Wang, Z., Zhao, L., & Fan, X. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322944
“Studies like Chen et al. [18] optimized wireless KD-FL convergence and efficiency, but single-objective focus neglected accuracy-communication balance.”
Strategic Federated Learning: A Novel Game-Theoretic Approach to Secure and Efficient IoD
Sekhar, K. C., Varshini, D. V. D. S., Lakshmi, S. G. N. S., & Yogi, M. K. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4277-1.ch007
Arisdakessian, S. (2025) · PolyPublie (École Polytechnique de Montréal)
Optimising privacy protection for cross-border data flow based on federated learning
Niu, F. (2026) · International Journal of Information and Communication Technology · doi:10.1504/ijict.2026.152200
Rajput, N. S., Mishra, A., & Rajput, N. S. (2025) · International Conference on Computational Intelligence and Network Systems (CINS) · doi:10.1109/cins67018.2025.11412183
“While prior work has studied FL in vehicular networks [5] or IoT systems [6] independently, none has unified vehicular, pedestrian, and crowd data into a single framework validated with both documented real-world failures [11], [12] and digital twin simulations [7], [8].”
InfluentialHe, Q., Chen, X., Li, Y., & Gu, C. (2025) · International Conference on Power Systems, Smart Grid, and Artificial Intelligence (PSGAI) · doi:10.1109/psgai68158.2025.11413441
“Device heterogeneity manifests through divergent data volumes, heterogeneous computational capacities, and dispersed geographical distributions across edge devices [6].”
Energy-Efficient User Grouping-Based Federated Learning With UAV Assistance
Fu, C.-W., Ku, M., & Singh, K. K. (2026) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2026.3676914
“Works such as [15], [19] [25], [26], and [28] derive convergence bounds under fixed accuracy levels to reduce communication rounds, whereas [31], [32], and [33] assume a single local update per round, which is unrealistic in practice.”
Jin, H., Zhou, Y., Sheng, Q. Z., Wen, S., & Cui, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464057
Ren, Y., Wu, C., So, D. K. C., & Ding, Z. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3693730
“To address statistical heterogeneity, IS was adopted in [9] and [15] to probabilistically schedule users based on their gradient norms.”
InfluentialConvergence-Driven Federated Learning with Joint Compression and Computation Optimization
Zhan, M., Chan, K., & Ji, M. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571582
“Several recent studies have addressed these challenges by developing targeted optimization approaches to enhance FL performance [6]–[11].”
Secure and Dynamic Node Selection in Federated Learning: A Reputation-Based Approach with Blockchain
Zheng, K., Hei, Y., Bai, C., Fan, D., Xu, Z., Wu, T., Wang, Y.-X., Liu, J., & Zhou, D. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9284-5_5
Li, Z., Liu, J., Luo, M., Li, L., & Dong, P. (2026) · Mechanisms and machine science · doi:10.1007/978-3-032-11165-4_88
Federated Deep Reinforcement Learning for Energy-Efficient Resource Optimization in 6G Network
Chaudhary, S., & Vishnoi, V. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.077
Alamoudi, A. M., & Almansouri, A. S. (2026) · Journal Of Big Data · doi:10.1186/s40537-026-01526-1
“Chen et al. [53] studied FL deployment in real wireless networks and proposed a client selection strategy that more frequently selects network users who contribute most to FL convergence, thereby optimizing performance while minimizing convergence time.”
Client selection of multi-criteria and adaptive deadline in federated learning
Gao, Z., Sun, Y., Zhang, L., Wang, R., & Zhu, H. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108777
Joint User Selection, Power Control and Channel Assignment for Wireless Federated Learning
Bai, J., Liu, F., Ji, H., & Wang, X. (2026) · Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC) · doi:10.1109/csrswtc71154.2026.11669197
“To thoroughly assess the effectiveness of our proposal, we introduce three representative benchmark schemes for user selection: gradient-based [10], random selection, and data-volume-only selection.”
A Review of Resource Allocation Strategies for Federated Learning in Wireless Networks
Fath, N., Nugraha, I. G. D., & Asvial, M. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3730823
“Some studies optimize device scheduling and resource allocation jointly at each global iteration [88], [89], while other studies extend the optimization aspect to a long-term perspective by minimizing system costs in terms of energy consumption and time delay over multiple rounds [90], [91], or…”
Fluid antenna assisted federated unlearning system
Chen, Y., Yang, Z., Xu, H., Ceng, C., Chen, Y., Wong, K., & ZHANG, C. (2026) · Scientia Sinica Informationis · doi:10.1360/ssi-2026-0205
Hidden in Rounds: Predicting the Time Cost of 802.11 Contention in Federated LearningPreprint
Bashir, S., & Dagiuklas, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.12903
Wang, C., Zhang, X., Wei, Z., Zhao, L., Yang, Z., & Feng, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.14246
“Physical Layer [25], [26] Signal quality enhancement Hardware reliance Resource optimization [6], [7], [27]–[31] Communication and computing resource”
Aburbeian, A. M., Fernández‐Veiga, M., Vilas, A. F., Owda, M., & Owda, A. Y. (2026) · Future Internet · doi:10.3390/fi18090484
Beamforming-Aided Wireless Multimodal Federated Learning: Dynamic Pruning and Joint Optimization
Xie, C., Chen, Z., Yi, W., Shin, H., & Nallanathan, A. (2026) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc70295.2026.11680208
“Wireless FL has been widely studied from the perspectives of client selection, joint communication-learning design, adaptive model pruning, and beamforming [6]–[10].”
Zhao, Y., Li, B., Xu, C., Zhang, J., & Wang, L. (2026) · Sensors · doi:10.3390/s26196181
Ram, D., Gyanchandani, M., & Rasool, A. (2025) · International Journal of Environmental Sciences · doi:10.64252/3hcb0131
Straggler-Resilient Hierarchical Split Federated Learning via Smashed Data Generation
Xie, C., Chen, Z., Yi, W., Xing, H., Lam, C., & Nallanathan, A. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3739323
Hoxha, J., Panxhi, M., & Thanasi-Boçe, M. (2026) · IEEE Access · doi:10.1109/access.2026.3743411
Murali, K. H., Ramadevi, P., Shyam Kishore, G., Pushpalatha, M., Bandhekar, S. K., & Chaitanya, M. (2026) · Acta Innovations · doi:10.62441/actainnovations.vi.2720
Supporting information 5 of Applications and Techniques for Fast Machine Learning in Science
Deiana, A. M., Tran, N., Agar, J., Blott, M., Guglielmo, G. D., Duarte, J., Harris, P., Hauck, S., Liu, M., Neubauer, M. S., et al. (2022) · doi:10.3389/fdata.2022.787421.s005
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.