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 101–200 of 444
Shi, D., Li, L., Wu, M., Shu, M., Yu, R., Pan, M., & Han, Z. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3189320 · Cited by 50
“Furthermore, Chen et al. [20], [21] established a joint user selection and resource block allocation scheme to minimize the convergence time and optimize the FL performance.”
BackgroundZhou, Y. F., Lei, L., Zhao, X., You, L., Sun, Y., & Chatzinotas, S. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2024.3365902 · Cited by 49
“Chen et al. [11] proposed a probabilistic device selection scheme to accelerate the global model convergence in FL systems.”
BackgroundLuo, L., Zhang, C., Yu, H., Sun, G., Luo, S., & Dustdar, S. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3399649 · Cited by 49
Adaptive Semi-Asynchronous Federated Learning Over Wireless Networks
Chen, Z., Yi, W., Shin, H., & Nallanathan, A. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3425635 · Cited by 49
“To boost the learning efficiency of synchronous FL, existing studies have primarily concentrated on optimizing resource allocation [12], client selection policies [13]–[15], and their collaborative design [16], [17].”
BackgroundMethodComputation Offloading and Resource Allocation Based on DT-MEC-Assisted Federated Learning Framework
He, Y., Yang, M., He, Z., & Guizani, M. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3298926 · Cited by 48
“Chen et al. [18] designed a user selection scheme to select appropriate users to participate in FL training, and combined with wireless resource allocation to improve the model convergence speed.”
BackgroundAdaptive asynchronous federated learning
Lu, R., Zhang, W., Li, Q., He, H. X., Zhong, X., Yang, H., Wang, D., Xu, Z., & Alazab, M. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.11.001 · Cited by 48
Zhang, H., Zhao, H., Liu, R., Gao, X., & Xu, S. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3376256 · Cited by 48
Zheng, J., Tian, H., Ni, W., Ni, W., & Zhang, P. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3188502 · Cited by 47
Wu, B., Fang, F., Wang, X., Cai, D., Fu, S., & Ding, Z. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3411479 · Cited by 46
“…Considering the resource bottleneck in the two-layer FL systems, a variety of mechanisms have been proposed to improve FL performance in existing works, including model compression [8], [9], client scheduling [10], [11], [12], [13], [14] and resource allocation [15], [16], [17], [18], [19].”
BackgroundMethodJoint Optimization of Energy Consumption and Completion Time in Federated Learning
Zhou, X., Zhao, J., Han, H., & Guet, C. (2022) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs54860.2022.00101 · Cited by 46
Arisdakessian, S., Wahab, O. A., Mourad, A., & Otrok, H. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3246988 · Cited by 44
“The authors of [19] also investigate the problem of client selection inside wireless networks.”
BackgroundEl‐kenawy, E. M., Alhussan, A. A., Eid, M. M., & Ibrahim, A. F. (2024) · Frontiers in Environmental Science · doi:10.3389/fenvs.2024.1417664 · Cited by 43
Distributed Machine Learning for Autonomous Agent Swarm: A Survey
Hou, X., Wang, J., Du, J., Jiang, C., & Ren, Y. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3594713 · Cited by 44
“Moreover, the work presented in [156] formulates a training time minimization problem by optimizing agent selection and bandwidth allocation.”
FedFog: Network-Aware Optimization of Federated Learning Over Wireless Fog-Cloud Systems
Nguyen, V., Chatzinotas, S., Ottersten, B., & Duong, T. Q. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3167263 · Cited by 42
“The promising approaches to mitigating the straggler effect include user sampling [5], [23], [35] and user selection [36]–[38], which require only a subset of users to participate in the training process.”
BackgroundAnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices
Li, P., Cheng, G., Huang, X., Kang, J., Yu, R., Wu, Y., & Pan, M. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229017 · Cited by 42
Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks
Hu, Y., Chen, M., Saad, W., Poor, H. V., & Cui, S. R. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322414 · Cited by 41
Self-citationImteaj, A., & Amini, M. H. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.657653 · Cited by 41
“Some recent FL works (Dinh et al., 2019; Haddadpour and Mahdavi, 2019; Wang et al., 2019; Chen et al., 2020a; Guo et al., 2020; Nguyen et al., 2020) analyze how to guarantee convergence both in theoretically and empirically for an FL setting.”
BackgroundTime-Sensitive Learning for Heterogeneous Federated Edge Intelligence
Xiao, Y. L., Zhang, X., Li, Y., Shi, G., Krunz, M., Nguyen, D. N., & Hoang, D. T. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3237374 · Cited by 41
Federated Learning With Over-the-Air Aggregation Over Time-Varying Channels
Tegin, B., & Duman, T. M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3235894 · Cited by 40
Feng, C., Wang, Y., Zhao, Z., Quek, T. Q. S., & Peng, M. (2020) · 2020 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops49005.2020.9145182 · Cited by 34
“In the MEC systems, the optimization design of federated learning is studied in [4], [5].”
BackgroundJoint Gradient Sparsification and Device Scheduling for Federated Learning
Lin, X., Liu, Y., Chen, F., Ge, X., & Huang, Y. (2023) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2023.3239373 · Cited by 39
“Another research area of federated learning is resource management, which can be further divided into energy minimization [15], [16], [17], [18], [19], [20], delay minimization [20], [21], [22], [23], [24] and training performance improvement [20], [25], [26], [27], [28].”
BackgroundConvergence Acceleration in Wireless Federated Learning: A Stackelberg Game Approach
Wang, K., Ma, Y., Mashhadi, M. B., Foh, C. H., Tafazolli, R., & Ding, Z. J. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3452933 · Cited by 39
“Therefore, in any round, the set of selected devices N t and the set of device selection indicators S (t) can be mutually inferred.”
Yan, Z., & Li, D. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3322461 · Cited by 38
Resources-Efficient Adaptive Federated Learning for Digital Twin-Enabled IIoT
Qiao, D., Li, M., Guo, S., Zhao, J., & Xiao, B. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3382206 · Cited by 38
Liu, P., Jiang, J., Zhu, G., Cheng, L., Jiang, W., Luo, W., Du, Y., & Wang, Z. (2022) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2100538 · Cited by 38
“The authors in [7] minimized the training time for a fixed communication rounds by solving a joint learning, wireless resource allocation, and device selection problem.”
BackgroundAlbaseer, A. M., Abdallah, M. M., Al‐Fuqaha, A., Erbad, A., & Dobre, O. A. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3194833 · Cited by 37
“For instance, the works in [17] and [19] studied the convergence analysis of the FL training algorithms over wireless channels considering the impact of unreliable links on the convergence rate.”
BackgroundFederated Learning for 6G: Paradigms, Taxonomy, Recent Advances and InsightsPreprint
Driss, M. B., Sabir, E., Elbiaze, H., & Saad, W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.04688 · Cited by 38
“To address the inherently unreliable connectivity in FL, the authors of [294], [295] consider error correction coding, adaptive modulation and coding schemes, robust aggregation algorithms, and the use of redundant data transmission.”
MethodSelf-citationAdaptive Heterogeneous Client Sampling for Federated Learning Over Wireless Networks
Luo, B., Xiao, W., Wang, S., Huang, J., & Tassiulas, L. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3368473 · Cited by 37
Edge-Assisted Democratized Learning Toward Federated Analytics
Pandey, S. R., Nguyen, M. N. H., Dang, T. N., Tran, N. H. K., Thar, K., Han, Z., & Hong, C. S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3085429 · Cited by 36
“Similarly, in [15] and [9], the authors focused on minimizing learning time while improving communication efficiency to realize FL over wireless networks.”
BackgroundEnhancing Federated Learning With Spectrum Allocation Optimization and Device Selection
Zhang, T., Lam, K., Zhao, J., Li, F., Han, H., & Jamil, N. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2022.3231986 · Cited by 36
“However, the impact of CPU frequency were not considered by [38]–[41]; whereas, individual energy constraints were not addressed in [36], [38], [39]; the data distribution of the local datasets were not addressed by [37], [39], [40].”
BackgroundGraph Federated Learning for CIoT Devices in Smart Home Applications
Rasti-Meymandi, A., Sheikholeslami, S. M., Abouei, J., & Plataniotis, K. N. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3228727 · Cited by 35
“Some other researches, such as [36], provided a device selection scheme where only devices with the most contribution are chosen to reduce the number of communication round, while another group focused on the network resource management [37], [38].”
BackgroundGao, Y., Liu, M., Yuan, X., Hu, Y., Sun, P., & Schmeink, A. (2024) · Scientific Reports · doi:10.1038/s41598-024-72654-y · Cited by 34
Edge Learning with Timeliness Constraints: Challenges and Solutions
Sun, Y., Shi, W., Huang, X., Zhou, S., & Niu, Z. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.2000382 · Cited by 34
“For the unscheduled devices, ML-based estimation techniques can be further leveraged to predict their local model updates at the edge server in order to improve the convergence rate [7].”
BackgroundMethodJoint Coding and Scheduling Optimization for Distributed Learning Over Wireless Edge Networks
Huynh, N. V., Hoang, D. T., Nguyen, D. N., & Dutkiewicz, E. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118432 · Cited by 34
Optimizing Federated Learning on Device Heterogeneity with A Sampling Strategy
Xu, X., Duan, S., Zhang, J., Luo, Y., & Zhang, D. (2021) · International Workshop on Quality of Service · doi:10.1109/iwqos52092.2021.9521361 · Cited by 34
Federated Learning for Air Quality Index Prediction using UAV Swarm Networks
Chhikara, P., Tekchandani, R., Kumar, N., Tanwar, S., & Rodrigues, J. J. P. C. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685991 · Cited by 34
“Authors in [22] optimized the FL convergence time by utilizing the capabilities of collective learning and wireless resource allocation.”
MethodOptimizing the Numbers of Queries and Replies in Convex Federated Learning With Differential Privacy
Zhou, Y., Liu, X., Fu, Y., Wu, D., Wang, J. H., & Yu, S. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3234599 · Cited by 35
Fast Convergence Algorithm for Analog Federated Learning
Xia, S., Zhu, J., Yang, Y., Zhou, Y., Shi, Y., & Chen, W. (2021) · ICC 2021 - IEEE International Conference on Communications · doi:10.1109/icc42927.2021.9500875 · Cited by 33
“Many digital communication based approaches have recently been proposed to facilitate FL in wireless networks [7]–[11], where each edge device is assigned an orthogonal channel to upload its local model.”
BackgroundFederated Learning for Energy-Efficient Task Computing in Wireless Networks
Wang, S., Chen, M., Saad, W., & Yin, C. (2020) · ICC 2020 - 2020 IEEE International Conference on Communications (ICC) · doi:10.1109/icc40277.2020.9148625 · Cited by 33
“Given W n , (9) can be rewritten as: From (13), we can see that compared to the standard FL algorithms [13] that directly average the learning parameters W n , the proposed FL algorithm uses a matrix Ω n to find the relationship among all users’ association and, hence, improving the FL prediction…”
BackgroundSelf-citationAge-of-Information Minimization in Federated Learning Based Networks With Non-IID Dataset
Wang, K., Ding, Z., So, D. K. C., & Ding, Z. J. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3357208 · Cited by 33
“In order to guarantee the convergence, a binary convergence indicator was introduced to minimize the number of required communication rounds [10].”
BackgroundCommunication-Efficient Federated Multitask Learning Over Wireless Networks
Ma, H., Guo, H., & Lau, V. K. N. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3201310 · Cited by 32
“By contrast, user scheduling is adopted to obtain an approximate gradient ˆ g ( t ) to seek a good tradeoff between the training convergence rate and the per-round communication overhead [26], [37], [38], [39], [40], [41], [42], [43], [44].”
BackgroundMethodInfluentialEnhanced Hybrid Hierarchical Federated Edge Learning Over Heterogeneous Networks
Chen, Q., You, Z., Wen, D., & Zhang, Z. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3287355 · Cited by 32
Hu, F., Deng, Y., & Aghvami, A. H. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3126147 · Cited by 31
Exploring Representativity in Device Scheduling for Wireless Federated Learning
Chen, Z., Yi, W., & Nallanathan, A. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3281765 · Cited by 31
“The scheduling policies that measure device importance based on gradient norm [21], [22], inner product [23], or the diversity of local dataset [24] trend to schedule devices with similar gradient information in each round.”
BackgroundMethodResultInfluentialTime Minimization in Hierarchical Federated Learning
Liu, C., Chua, T. J., & Zhao, J. (2022) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec54971.2022.00015 · Cited by 30
“Papers such as [8], [9] established optimization problems which optimize variables such as UE uplink bandwidth and devices selection with the aim of minimizing FL convergence time.”
BackgroundFedProf: Selective Federated Learning based on Distributional Representation Profiling
Wu, W., He, L., Lin, W., & Maple, C. R. (2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2023.3265588 · Cited by 30
“More details are provided in Appendix B.1, available in the online supplemental material.”
BackgroundPerformance-Oriented Design for Intelligent Reflecting Surface-Assisted Federated Learning
Zhao, Y., Wu, Q., Chen, W., Wu, C., & Poor, H. V. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3283799 · Cited by 30
“, communication and computation resources) [17] or reduce resources consumption while maintaining satisfactory learning performance [18].”
BackgroundSelf-citationUAV-Enabled Federated Learning in Dynamic Environments: Efficiency and Security Trade-Off
Fan, X., Chen, Y., Liu, M., Sun, S., Liu, Z., Xu, K., & Li, Z. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3347912 · Cited by 30
Fu, Z., Liu, J., Mao, Y., Qu, L., Xie, L., & Wang, X. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3531237 · Cited by 31
“To solve this local optimization problem, we perform gradient descent on Δ k [13], [31]: where ρ is the step size, Δ ( n ) , ( i ) k represents the value of Δ k in the i -th local iteration given the global model ω ( n ) , and in the n -th iteration.”
ns3-fl: Simulating Federated Learning with ns-3
Ekaireb, E., Yu, X., Ergun, K., Zhao, Q., Lee, K., Huzaifa, M., & Rosing, T. (2022) · Workshop on ns-3 (WNS3) · doi:10.1145/3532577.3532591 · Cited by 29
“The baseline for much of the recent research in the field is FedAvg [16] which is an algorithm for synchronous FL. Recent work includes developing client selection policies [22] and manipulating resource allocation to improve convergence [2, 25].”
BackgroundDeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio
Ahmad, A., Agarwal, S., Darshi, S., & Chakravarty, S. (2022) · IEEE Access · doi:10.1109/access.2022.3219090 · Cited by 29
“The authors in [26], [27], and [28] proposed a machine learning method to optimize performance of wireless communication system.”
BackgroundWu, J., Dai, T., Guan, P., Liu, S., Gou, F., Taherkordi, A., Li, Y., & Li, T. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3367946 · Cited by 29
“In[31],[32], [33], and [34], a joint optimization problem was proposed with the objective of minimizing training latency.”
BackgroundSpace–Air–Ground–Sea Integrated Network with Federated Learning
Zhao, H., Ji, F., Wang, Y., Yao, K., & Chen, F. (2024) · Remote Sensing · doi:10.3390/rs16091640 · Cited by 30
“Furthermore, to minimize the FL convergence time and the FL training loss, a probabilistic user-selection scheme was proposed such that the BS was connected to the users whose local FL models had significant effects on the global FL model with high probabilities [27–29].”
Blind Federated Learning at the Wireless Edge With Low-Resolution ADC and DAC
Tegin, B., & Duman, T. M. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3087594 · Cited by 29
“In [7], the authors focus on the minimization of the convergence time of a federated learning system by jointly considering user selection and resource allocation.”
BackgroundResource Consumption for Supporting Federated Learning in Wireless Networks
Liu, Y., Qin, S., Sun, Y., & Feng, G. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3181611 · Cited by 28
“The authors of [6] designed an appropriate user selection scheme to minimize FL convergence time and training loss by jointly optimizing user selection and resource block allocation.”
MethodAwotunde, J. B., Sur, S. N., Jimoh, R. G., Aremu, D. R., Do, D., & Lee, B. M. (2023) · IEEE Access · doi:10.1109/access.2023.3335245 · Cited by 28
Towards Energy-Aware Federated Learning via Collaborative Computing Approach
Arouj, A., & Abdelmoniem, A. M. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.04.012 · Cited by 28
Li, P., Cheng, G., Huang, X., Kang, J., Yu, R., Wu, Y., Pan, M., & Niyato, D. T. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3245601 · Cited by 27
“Being in line with existing studies [34], [35], we make the following assumptions for the global loss and the local loss.”
ResultTowards Instant Clustering Approach for Federated Learning Client Selection
Arisdakessian, S., Wahab, O. A., Mourad, A., & Otrok, H. (2023) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc57223.2023.10074237 · Cited by 27
“The authors of [9] also investigate the notion of client selection inside wireless networks.”
BackgroundDistributed and Democratized Learning: Philosophy and Research Challenges
Nguyen, M. N. H., Pandey, S. R., Thar, K., Tran, N. H. K., Chen, M., Saad, W., & Hong, C. S. (2021) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.3039068 · Cited by 27
“Correspondingly, numerous research activities in machine learning technologies [1]–[8] focused on architectures and algorithm designs that empowered the emergence of cross-device AI applications in our daily lives.”
BackgroundSelf-citationCommunication-Efficient Federated Edge Learning for NR-U-Based IIoT Networks
Chen, Q., Xu, X., You, Z., Jiang, H., Zhang, J., & Wang, F. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3136205 · Cited by 27
“Moreover, a joint user selection and resource allocation scheme is investigated in [9], whose goal is to minimize the FEL convergence time via probabilistic scheduling.”
BackgroundMethodZhang, J., Chen, S., Zhou, X., Wang, X., & Lin, Y. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3148208 · Cited by 26
“More specifically, in [13], [14], a neural network is designed to predict the parameters of local models of the participants failed in uploading, so as to alleviate the impacts of transmission failure.”
BackgroundMethodInfluentialFederated Learning in UAV-Enhanced Networks: Joint Coverage and Convergence Time Optimization
Yahya, M., Maghsudi, S., & Stańczak, S. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3330010 · Cited by 26
“There are different methods to address this issue, such as client selection (CS) [6], [7], [8], [9], [10], [11], resource allocation [12], [13], and update compression [14].”
MethodDistributed Constrained Online Convex Optimization Over Multiple Access Fading Channels
Cao, X., & Başar, T. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3185897 · Cited by 25
Gradient sparsification for efficient wireless federated learning with differential privacy
Wei, K., Li, J., Ma, C., Ding, M., Shu, F., Zhao, H., Chen, W., & Zhu, H. (2024) · Science China Information Sciences · doi:10.1007/s11432-023-3918-9 · Cited by 25
“Further, the works in [8] and [9] improved the training efficiency based on the convergence bound by optimizing the client selection and power allocation via constructing the connection between the wireless resource allocation and the FL training performance using the convergence bound.”
BackgroundAl-Shamasneh, A. R., Karim, F. K., & Wang, Y. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106387 · Cited by 24
Han, D.-J., Fang, W., Hosseinalipour, S., Chiang, M., & Brinton, C. G. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2024.3459090 · Cited by 25
“Most of them consider a single-server setup [1], [4], [14], [15], [16], [17] while some researchers also study multi-server scenarios [5], [6], [18], [19], [20].”
Privacy in the Cloud: A Survey of Existing Solutions and Research Challenges
Silva, P. V. S., Monteiro, E., & Simões, P. (2021) · IEEE Access · doi:10.1109/access.2021.3049599 · Cited by 24
Tang, J., Li, X., Li, H., Li, P., Wang, X., & Leung, V. C. M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3539284 · Cited by 23
Enabling Ubiquitous Non-Orthogonal Multiple Access and Pervasive Federated Learning via STAR-RIS
Ni, W., Liu, Y., Eldar, Y. C., Yang, Z., & Tian, H. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685556 · Cited by 23
“Specifically, the convergence rate of FL was analyzed in [1], [9], whose results were extended to analog aggregation scenarios in [8], and a digital version was developed in [3].”
BackgroundDeep reinforcement learning based scheduling strategy for federated learning in sensor-cloud systems
Zhang, T., Lam, K., & Zhao, J. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.03.009 · Cited by 23
Salehi, B., Roy, D., Gu, J., Dick, C., & Chowdhury, K. R. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3401046 · Cited by 23
“A total of M + N probe frames or SSBs must be transmitted and the sector that returns the maximum received signal strength is then selected as the optimum sector.”
Federated Reinforcement Learning for Collaborative Intelligence in UAV-Assisted C-V2X Communications
Gupta, A., & Fernando, X. N. (2024) · Drones · doi:10.3390/drones8070321 · Cited by 23
Random Orthogonalization for Federated Learning in Massive MIMO Systems
Wei, X., Shen, C., Yang, J., & Poor, H. V. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3302335 · Cited by 22
“Client scheduling and various power and computation resource allocation methods have been investigated [26], [27], [28], [29], [30], [31].”
MethodSelf-citationFeng, X., Wang, X., Liu, H., Yang, H., & Wang, L. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3369942 · Cited by 22
Adaptive Model Pruning and Personalization for Federated Learning Over Wireless Networks
Liu, X., Ratnarajah, T., Sellathurai, M., & Eldar, Y. C. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3459808 · Cited by 22
“A probabilistic device selection scheme [29] was proposed to minimize the FL convergence time and the FL training loss in a joint learning, wireless resource allocation, and user selection problem.”
BackgroundMethodWireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems
Huang, W., Yang, Y., Chen, M., Liu, C., Feng, C., & Poor, H. V. (2021) · Entropy · doi:10.3390/e23111413 · Cited by 22
“In addition, the authors of [16] formulated an optimization problem of resource allocation and introduced the use of artificial neural networks (ANNs) to predict the unselected users’ FL model parameters to improve the FL convergence speed and training loss.”
BackgroundSelf-citationNguyen, T., Ho, N. D., HOANG, T. H., Do, C., & Wong, K. (2022) · IEEE Access · doi:10.1109/access.2022.3215758 · Cited by 21
“In [32], the authors optimize the radio resources by scheduling the devices to minimize the convergence time of FL.”
BackgroundAnalysis and evaluation of synchronous and asynchronous FLchain
Wilhelmi, F., Giupponi, L., & Dini, P. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109390 · Cited by 21
“Under these circumstances, it is challenging to provide convergence proofs, but several works advocate for speeding up performance through complementary tools like estimating the missing local updates through DL [56].”
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Yuan, H., Hui, B., Yang, Y., Burlina, P., Gong, N. Z., & Cao, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_11 · Cited by 20
“Existing federated learning (FL) studies focus on improving accuracy [35,50,43,39], convergence [12,6,37,17,45,32], communication cost [24,41,22,3,23,13,34,49], security and privacy [36,10,5,4], or others [16,20,11,47].”
BackgroundTopology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
Wu, Z., Xu, Z., Zeng, D., Li, J., & Liu, J. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3376708 · Cited by 20
“Index Terms —D2D networks, data heterogeneity, decentralized federated learning, topology learning, unreliable links.”
BackgroundA Survey on Federated Learning for Reconfigurable Intelligent Metasurfaces-Aided Wireless Networks
Das, S. K., Champagne, B., Psaromiligkos, I., & Cai, Y. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3378266 · Cited by 20
“To ensure the efficacy of the FL process under poor channel conditions, the study in [37] explores various strategies including the development of resilient aggregation algorithms, the implementation of error correction coding, the use of redundant data transmission, and the adoption of adaptive…”
MethodMa, X., Yin, C., & Liu, X. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345069 · Cited by 20
Lightweight Federated Learning Over Wireless Edge Networks
Hou, X., Wang, J., Du, J., Jiang, C., Ren, Y., & Niyato, D. T. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3594102 · Cited by 19
Chen, S., Li, L., Wang, G., Pang, M., & Shen, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3296493 · Cited by 19
“The work in [35], [36], [37], and [38] investigated joint FL, user selection schemes, and wireless resource allocation.”
BackgroundMobility-Aware Routing and Caching in Small Cell Networks Using Federated Learning
Cao, Y., Maghsudi, S., Ohtsuki, T. O., & Quek, T. Q. S. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3327278 · Cited by 19
“Besides, the FL concept is a widespread tool for wireless edge network optimization [9], [10], [11], [12], [13], due to the following three reasons: (i) The ever-increasing number of devices in the internet of things (IoT) generate an enormous amount of data at the network edge.”
BackgroundOptimal Mechanism Design for Heterogeneous Client Sampling in Federated Learning
Liao, G., Luo, B., Feng, Y., Zhang, M., & Chen, X. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3379659 · Cited by 19
Joint Client Selection and Model Compression for Efficient FL in UAV-Assisted Wireless Networks
Chen, L., Wang, R., Cui, Y., He, P., & Duan, A. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3410178 · Cited by 19
Lu, R., Zhang, W., He, H. X., Li, Q., Zhong, X., Yang, H., Wang, D., Shi, L., Guo, Y., & Wang, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3431555 · Cited by 19
“Many of those works [37], [38], [39], [40] focused on building an efficient selection scheme that helps improve the performance of FL under data heterogeneity scenarios.”
BackgroundOn the Convergence Time of Federated Learning Over Wireless Networks Under Imperfect CSI
Pase, F., Giordani, M., & Zorzi, M. (2021) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops50388.2021.9473615 · Cited by 19
Client Selection for Asynchronous Federated Learning with Fairness Consideration
Zhu, H., Yang, M., Kuang, J., Qian, H. L., & Zhou, Y. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814669 · Cited by 19
Dynamic Resource Optimization for Adaptive Federated Learning at the Wireless Network Edge
Lorenzo, P. D., Battiloro, C., Merluzzi, M., & Barbarossa, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414832 · Cited by 19
“Finally, reference [22] proposes a dynamic user selection scheme to minimize the FL convergence time.”
BackgroundDistributed Learning Over Networks With Graph-Attention-Based Personalization
Tian, Z., Zhang, Z., Yang, Z., Jin, R., & Dai, H. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3282071 · Cited by 17
“challenges, some recent progress has been made on the communication-efficient implementation of FL in wireless communication system [24], [25], [26], [27], through resource allocation [24], [25], reducing communication cost per iteration [26] and accelerating convergence [27].”
BackgroundFernando, X. N., & Gupta, A. (2024) · Sensors · doi:10.3390/s24248186 · Cited by 16
Efficient Asynchronous Federated Learning for AUV Swarm
Meng, Z., Li, Z. Z., Hou, X., Du, J., Chen, J., & Wei, W. (2022) · Sensors · doi:10.3390/s22228727 · Cited by 16
“In [16], the author selects some clients to send their local model parameters to the server, avoids the training loss, and convergence time being affected by a reasonable local selection strategy, and establishes an optimization problem to optimize the convergence time and training loss, using ANN (artificial neural n…”
BackgroundSemi-Asynchronous Hierarchical Federated Learning Over Mobile Edge Networks
Chen, Q., You, Z., Wu, J., Liu, Y., & Jiang, H. (2022) · IEEE Access · doi:10.1109/access.2022.3227561 · Cited by 16
Özfatura, E., Zhao, J., & Gündüz, D. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593130 · Cited by 16
Energy-Efficient Active Federated Learning on Non-IID Data
Shullary, M. H., Abdellatif, A. A., & Massoudn, Y. (2022) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas54063.2022.9859532 · Cited by 16
“The selection of users participating in the FL process was investigated in [5], [6], [7], while in [8], [9], [10] various compression and sparsification techniques are proposed to minimize the communication costs of FL.”
BackgroundEfficient Federated Learning via Joint Communication and Computation Optimization
Wang, G., Zhao, C., Qi, Q., Han, R., Bai, L., & Choi, J. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3379742 · Cited by 16
Federated Learning Via Nonorthogonal Multiple Access for UAV-Assisted Internet of Things
Ren, P., Wang, J., Tong, Z., Chen, J., Pan, P., & Jiang, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3413780 · Cited by 15
“To facilitate subsequent analysis, we redefine (1) as and give assumptions as follows [40].”
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.