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 301–400 of 444
Multi-Attribute Auction-Based Grouped Federated Learning
Lu, R., Yang, H., Wang, Y., He, H. X., Li, Q., Zhong, X., & Zhang, W. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3387734 · Cited by 4
Xie, J., Jia, Q., & Chen, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3469956 · Cited by 4
Joint Job Assignment and Resource Allocation for Multi-Job Wireless Federated Learning
Li, T. K., Wei, Z., Liu, H., Lin, Z., & Chan, T.-T. (2024) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass62177.2024.00062 · Cited by 4
“Some research focuses on minimizing training delays [7] or reducing the total energy cost [8], [9] to improve WFL system efficiency.”
BackgroundBenchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentation
Innocenti, L., Antonelli, M., Cremonesi, F., Sarhan, K., Granados, A., Goh, V., Ourselin, S., & Lorenzi, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-74640-6_5 · Cited by 4
Su, L., & Lau, V. K. N. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3177449 · Cited by 4
“In [21], a joint user scheduling and resource block allocation scheme is proposed to minimize the total convergence time throughout the training process.”
BackgroundMethodAdaptive Scheduling for Machine Learning Tasks over Networks
Gatsis, K. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9482692 · Cited by 4
Linear Regression over Networks with Communication Guarantees
Gatsis, K. (2021) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.2103.04140 · Cited by 4
Returning the Favor: What Wireless Networking Can Offer to AI and Edge LearningPreprint
Sorour, S., Mohammad, U., Abutuleb, A., & Hassanein, H. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07453 · Cited by 4
“Some recent works have started to investigate physical resource optimization for FL [10-12].”
BackgroundAl-Abiad, M. S., Hassan, M. Z., & Hossain, M. J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.00032 · Cited by 4
“Numbers of global iterations and duration of each global iteration were minimized by jointly optimizing the UD selection and RRB allocation [14].”
MethodMulti-Task Over-the-Air Federated Learning in Cell-Free Massive MIMO SystemsPreprint
Chen, C., Björnson, E., & Fischione, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.17874 · Cited by 4
Energy Efficiency in Federated Learning: A Survey on Models, Strategies and PerspectivesPreprint
Sezgin, S., Mokrani, K., Jacques, J., & Allio, S. (2025) · HAL · Cited by 4
Duan, Y., Wu, W., Yang, Z., & Zhu, S. (2025) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.7926 · Cited by 3
Wu, B., Fang, F., & Wang, X. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3580312 · Cited by 3
“Restrictions apply. where d n is the size of local model parameters which is assumed to be unique among all clients due to local models have similar numbers of elements [29].”
Zheng, P., Keshtiarast, N., Bishoyi, P. K., Zhu, Y. L., Hu, Y., Petrova, M., & Schmeink, A. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3635227 · Cited by 3
“In wireless FL (WFL), numerous works have concentrated on reducing the overall training latency while allocating both training and wireless resources [15], [16], [17], [18], [19], [20], [21], [22].”
Wang, Z., Wang, K., & Wang, J. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3654079 · Cited by 3
“…communication time, wireless bandwidth, transmission power, and FL model accuracy of devices to minimize the energy consumption of FL. Chen et al. [25] established the optimization problem of minimizing FL convergence time and loss function, and proposed the strategies of probabilistic user…”
Hoyos, E. A., Orozco, H. F. B., & Rodríguez-Idrobo, N. C. (2026) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan15030044 · Cited by 3
Distribution Deviation-Aware Split Federated Learning in Resource-Limited Wireless Networks
Xie, C., Chen, Z., Yi, W., Shin, H., & Nallanathan, A. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3706602 · Cited by 3
“Network setup: The simulation parameters follow representative wireless FL configurations (e.g., [23], [27], [39], [40]).”
An Energy-Efficient Intelligence Sharing Scheme in Intelligence Networking-Empowered Edge Computing
Xie, J., Jia, Q., & Lu, F. (2024) · IEEE Access · doi:10.1109/access.2024.3421652 · Cited by 3
Zheng, Z., Wang, Z., Tong, X., Li, K., & Chen, Q. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580393 · Cited by 3
“The transmission rate of client i is given by [18]. here, (3) formula is based on Shannon’s theorem and i = [ (cid:2) i 1 , . . . , (cid:2) ij , . . . , (cid:2) iR ] is an RB allocation vector with (cid:2) ij ∈ { 0 , 1 } ; (cid:2) ij = 1 indicates that the j -th RB is allocated to client i .”
BackgroundLearner Referral for Cost-Effective Federated Learning Over Hierarchical IoT Networks
Gao, Y., Ye, Z., Xiao, Y., Xiao, M., & Xiang, W. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3480053 · Cited by 3
“Among the early iconic contributions in this area, the authors of [6], [7], [8] proposed a probabilistic FedCS approach to minimize the training loss while guaranteeing model fast convergence.”
Approximate Wireless Communication for Lossy Gradient Updates in IoT Federated Learning
Ma, X., Sun, H., Hu, R. Q., & Qian, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3488377 · Cited by 3
“In [8] and [9], a joint problem of resource allocation and user selection is proposed to minimize the convergence time in FL. Advanced transmission schemes, such as nonorthogonal multiple access (NOMA) [10] offer promising solutions.”
Communication-Efficient Distributed Learning in Massive IoT: A Graph-Based Perspective
Zhao, L., Tang, J., Chen, M., Zhou, L., & Zhuang, W. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978625 · Cited by 3
“For example, a strand of literature alleviates communication burdens by relaxation-and-rounding algorithms [4], probabilistic policies [5] or priority-based mechanisms [6] to select devices with significant weight update or good channel conditions.”
Self-citationAir-FedGA: A Grouping Asynchronous Federated Learning Mechanism Exploiting Over-The-Air Computation
Ma, Q., Zhou, J., Hou, X., Liu, J., Xu, H., Miao, J., & Jia, Q. (2025) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps64566.2025.00051 · Cited by 3
“However, when deployed at the network edge, FL faces several challenges: 1) Limited communication resource : Traditional orthogonal multiple access (OMA) schemes (TDMA [5]–[7], OFDMA [8] [9]) are commonly used for FL model ag-gregations.”
IRS Aided Federated Learning: Multiple Access and Fundamental Tradeoff
Chen, G., Li, J., Cui, Y., Wu, Q., Ni, Y., Hua, M., & Lu, S. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3665183 · Cited by 3
“Regarding the multiple access for model uploading, the works [14], [15] demonstrated the superiority of non-orthogonal multiple access (NOMA) over time division multiple access (TDMA) in terms of both the objectives of latency and energy consumption.”
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
Wei, X., Wang, T., Huang, R., Shen, C., Yang, J., & Poor, H. V. (2026) · IEEE Transactions on Information Theory · doi:10.1109/tit.2026.3668977 · Cited by 3
“The exploration of client scheduling, along with various power and computation resource allocation techniques, has been investigated by [20], [21], [22], [23], and [24].”
Self-citationPhysical Layer Design Challenges for 6G Wireless
Singh, S. P. (2021) · Computer communications and networks · doi:10.1007/978-3-030-72777-2_4 · Cited by 3
Wang, J., & Guo, S. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3328931 · Cited by 3
“Compared with traditional orthogonal multiple access schemes [18], [19], [20], analog over-the-air computation (OAC) is a promising solution, which allows edge devices to simultaneously transmit their local updates using complete radio resources in an uncoded manner.”
BackgroundSong, F. (2023) · Journal of Information Systems Engineering & Management · doi:10.55267/iadt.07.14076 · Cited by 3
Efficient Wireless Federated Learning with Adaptive Model Pruning
Chen, Z., Yi, W., Lambotharan, S., & Nallanathan, A. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437211 · Cited by 3
“2 compares the proposed AMP-FL with the following benchmarks: 1) Synchronous FL [3], [14]: The scheduled devices transmit and train the entire model and upload to the edge server for aggregation.”
MethodUnequal error protection transmission for federated learning
Zheng, S., & Chen, X. (2022) · IET Communications · doi:10.1049/cmu2.12379 · Cited by 3
A Communication-efficient Semi Asynchronous Federated Learning Network in Power Grid
Luo, X., You, Z., Liao, R., Liu, F., & Liang, D. (2022) · IEEE International Conference on Cyber Security and Cloud Computing / IEEE International Conference on Edge Computing and Scalable Cloud (CSCloud/EdgeCom) · doi:10.1109/cscloud-edgecom54986.2022.00034 · Cited by 3
SIoT Selection, Clustering, and Routing for Federated Learning with Privacy-Preservation
Chung, M.-S., Wang, C.-H., Yang, D.-N., Lee, G.-S., Chen, W.-T., & Sheu, J. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838641 · Cited by 3
“For DP, parameters ε and δ are set to 25 [13] and 30 [17], respectively.”
BackgroundSafety-assured, real-time neural active fault management for resilient microgrids integration
Wan, W., Zhang, P., Bragin, M. A., & Luh, P. B. (2022) · iEnergy · doi:10.23919/ien.2022.0048 · Cited by 3
Heterogeneous Federated Learning for Balancing Job Completion Time and Model Accuracy
Zhou, R., Wang, R., Yu, J., Li, B., & Li, Y. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads56603.2022.00079 · Cited by 3
“The trade-off between time and accuracy brings new challenges and opportunities in FL training [6], [7].”
BackgroundLatency Minimization for Wireless Federated Learning with Heterogeneous Local Updates
Zhu, J., Shi, Y., Fu, M., Zhou, Y., Wu, Y., & Fu, L. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118880 · Cited by 3
“However, most recent studies on latency minimization for wireless FL failed to consider the heterogeneous local updates [8]–[11], [14], [17].”
BackgroundInfluentialFederated Learning with Internet of Things for Data Privacy and Security
Cherukuvada, S., Krishnaraj, N., & Bellam, K. (2023) · International Conference on Networking and Communications (ICNWC) · doi:10.1109/icnwc57852.2023.10127281 · Cited by 3
“The integration time and performance of FL is highly affected due to user scheduling for load [45].”
BackgroundDevice Scheduling and Bandwidth Allocation for Federated Learning over Wireless Networks
Zhang, T., Lam, K., & Zhao, J. (2023) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss59129.2023.10291589 · Cited by 3
Federated Learning Over Device-Centric Cell-Free Networks: A Long-Term Perspective
Dong, Z., Zhu, X., Cao, J., Tham, C., Yang, Z., & Lau, V. K. N. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3627796 · Cited by 2
“Some studies have aimed to improve long-term FL performance by lowering convergence costs [16], reducing convergence time [21], minimizing over-all energy consumption [22], and minimizing convergence gap [27].”
Computation and Communication Resource Optimization for Efficient Hierarchical Federated Learning
Liu, C., Zhao, J., & Wang, Y. L. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3600163 · Cited by 2
“The focus of papers such as [7] and [8] is to reduce FL convergence time by the optimization of factors like user equipments (UE) uplink bandwidth and device selection.”
HierTFL: Hierarchical Scheduling for Industrial TSN-Enhanced Federated Learning System
Zhang, X., Li, M.-Y., Guo, S.-T., Gu, F.-Q., Zhou, P.-Z., & Zhang, W. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3647455 · Cited by 3
Sun, H., Chen, M., Yang, Z., Cang, Y., Pan, Y., & Huang, K. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3644920 · Cited by 2
“However, all the above works [10], [11], [12], [13], [14], [15], [16], [17] primarily address single-task FL.”
Self-citationOn Transferring, Merging, and Splitting Task-Oriented Network Digital Twins
Zhang, Z., Fang, M., Chen, M., & Liu, Y. (2025) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1109/mswim67937.2025.11309199 · Cited by 2
“Many studies, such as [23], [24], [25], adopt distributed learning to handle various datasets efficiently while significantly reducing bandwidth usage, shedding light on challenges such as data heterogeneity and communication overhead.”
Self-citationA Semantic Communication-Assisted Federated Learning Framework for Internet of Vehicles
Luo, M., Mao, J., Xiong, G., & Anjum, M. R. (2026) · Journal of Intelligent Computing and Networking · doi:10.64509/jicn.21.74 · Cited by 2
“Second, communication latency significantly affects model convergence [14, 15].”
A Communication-Efficient Federated Learning by Dynamic Quantization and Free-Ride Coding
Chen, J., Wang, Q., Wan, H., & Ma, X. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10571243 · Cited by 2
Ashraf, Z., Sohail, A., & Iqbal, M. (2024) · Cryptography · doi:10.3390/cryptography8040049 · Cited by 2
Federated Learning-Distillation Alternation for Resource-Constrained IoT
da Silva, R. V., López, O. L. A., & Souza, R. D. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3671998 · Cited by 2
“Chen et al. [9] propose a probabilistic user selection scheme combined with artificial neural networks to estimate the local models of nonselected users, thereby improving the convergence time.”
An Asynchronous Federated Learning Optimization Scheme Based on Model Partition
Xu, J., Shi, L., Shi, Y., Chen, F., & Xu, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19211-1_31 · Cited by 2
One-shot federated learning with self-adversarial data
Danilenka, A., Bogacka, K., & Wasielewska-Michniewska, K. (2023) · Annals of Computer Science and Information Systems · doi:10.15439/2023f1102 · Cited by 2
Incentive-driven Federated Learning in Mobile Edge Networks
Zheng, Y., Zhou, H., Zhao, L., Xu, S., & Leung, V. C. M. (2023) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw60045.2023.00006 · Cited by 2
“In addition, from the perspective of BS, it is also a significant challenge to choose appropriate UEs participating in FL to minimize its training expenditure [15]-[16].”
BackgroundJoint Probability Selection and Power Allocation for Federated Learning
Marnissi, O., Hammouti, H. E., & Bergou, E. H. (2023) · IEEE Future Networks World Forum (FNWF) · doi:10.1109/fnwf58287.2023.10520398 · Cited by 2
“The authors of [11] formulated an optimization problem that jointly considers user selection and resource allocation to minimize the FL convergence time.”
BackgroundDou, K., He, F., Shang, F., Li, X., Dong, Y., & Liu, J. (2024) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai62182.2024.10692438 · Cited by 2
“There are two main types of federated learning: synchronous federated learning [5][6] and asynchronous federated learning [7][8].”
BackgroundFederated Learning Incorporating Non-Orthogonal Transmission and Unstructured Model Pruning
Gao, S., Zhao, M., & Zhou, S. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901154 · Cited by 2
“Aside from the proposed NOMA with pruning (NOMA-P), three baseline methods of wireless S-FL are listed as follows: 1) Original federated learning (O-FL) [13]: Traditional synchronous FL with the complete model distributed through BC. 2) BC with pruning(BC-P) : The lightweight core .”
Energy-Efficient Federated Learning for AIoT Using Clustering Methods
Pereira, R., Famá, F., Kalalas, C., & Dini, P. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3579583 · Cited by 2
“Unfortunately, while intuitive, this method has shown [16], [36], [37] only marginal improvements over random sampling in complex tasks (e.g., CIFAR-10 dataset).”
FedCGD: Collective Gradient Divergence Optimized Scheduling for Wireless Federated Learning
Chen, T., Yan, J., Sun, Y., Zhou, S., & Niu, Z. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3675454 · Cited by 2
“A large amount of studies have analyzed the convergence speed or equivalent expressions of wireless FL w.r.t. the scheduling policy [9], [16], [17], [18], [19], [20], [21], and proposed algorithms to optimize the long-term latency of FL [22], [23], [24], [25], [26], [27].”
Hybrid Dimming Scheme based on Transmit Antenna Selection and Precoding for MU MC VLC System
Yang, Y., Yang, Y., Wang, C., Guo, C., & Xia, H. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322424 · Cited by 2
Convergence Analysis of Cloud-Aided Federated Edge Learning on Non-IID Data
Wang, S., & Gong, Y. (2022) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51304.2022.9833971 · Cited by 2
A PPO-Based Dynamic Asynchronous Semi-Decentralized Federated Edge Learning
Li, Y., Zhang, Z., Fu, F., & Wang, Y. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads60453.2023.00083 · Cited by 2
“For example, a joint participant selection and resource optimization algorithm is proposed to minimize the convergence time of FL [6].”
BackgroundMohammad, U., & Saeed, F. (2024) · Big and integrated artificial intelligence · doi:10.1007/978-3-031-57567-9_3 · Cited by 2
FedProf: Efficient Federated Learning with Data Representation ProfilingPreprint
Wu, W., He, L., Lin, W., & Mao, R. (2021) · arXiv (Cornell University) · Cited by 2
Adaptive Biased User Scheduling for Heterogeneous Wireless Federate Learning NetworkPreprint
Wu, C., Ren, Y., So, D. K. C., & Tang, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.05231 · Cited by 2
“• Max Gradient [10], [15]: Schedule a certain proportion of users (10 users) with the probabilities proportional to their gradient norm.”
InfluentialBeyond Assumptions: Measuring Federated Learning over Real 5G NetworksPreprint
Hayek, R. J., Comer, K., Chung, J., Murthy, C. R., Kettimuthu, R., & Kadota, I. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.04678 · Cited by 2
“Existing literature that accounts for the wireless channel, e.g., [11, 29, 34, 36, 37], often assumes that the model upload occurs at rates comparable with the Shannon capacity [33].”
Muller, N. M., Derosa, S., Zhang, S., & Huan, C. L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.16881 · Cited by 2
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
Bourgerie, R., Girdzijauskas, Š., & Fodor, V. (2026) · Transactions on machine learning research · doi:10.48550/arxiv.2609.02984 · Cited by 2
Blind Federated Learning with Low-Cost Analog-to-Digital Converters
Tegin, B., & Duman, T. M. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685326 · Cited by 1
“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.”
BackgroundPriority-Aware Transmission for Federated Learning Over Wireless Networks
Yue, Y., Yao, J., Xu, J., Xu, W., Yang, Z., & Yuen, C. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11162025 · Cited by 1
“In [15], assigning higher probabilities of association with the PS to users with larger gradient norms resulted in significant improvements in convergence time.”
A Federated Distributed Spectrum Sharing Algorithm for UAV Swarm
Jia, A., Liao, X., Lu, Y., & Li, Q. (2025) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai66283.2025.11170565 · Cited by 1
“To accelerate the convergence of FL, Chen et al. proposed a probabilistic user selection scheme [12] that connects the base station to high-probability users with a significant impact on the global model, reducing the FL convergence time by 56%.”
Luo, Y., Jin, X. H., Xia, C., Xu, C., & Sun, Y. (2025) · Mathematics · doi:10.3390/math13233871 · Cited by 1
Resource- and Convergence-Aware Neural Algorithm Selection for 5G/B5G RAN
AlZailaa, A., Chi, H. R., Radwan, A., & Aguiar, R. L. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3653112 · Cited by 1
“Reference [18] extends FL with arti-ficial neural algorithms to approximate missing user updates; However, their model assumes idealized inference estimations and overlooks memory and energy trade-o ff s. Building on these directions, [19] applies transfer learning and DDQN to predict long-term…”
Pakravan, S., Ahmadzadeh, M., Zeng, M., Hodtani, G. A., Li, X., Wang, J., & Wang, G. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3686744 · Cited by 1
“At the same time, it is essential to carefully manage the resulting system complexity, which motivates the use of learning-based optimization approaches in this work.”
Hemalatha, V., & Pushpalatha, S. (2026) · International Conference on Advancements and Key Challenges in Green Energy and Computing (AKGEC) · doi:10.1109/akgec68790.2026.11485686 · Cited by 1
Yang, J., Ma, Y., Xiao, Z., & Han, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3692699 · Cited by 1
“Chen et al. [26] proposed a probabilistic user selection scheme and uplink resource block allocation scheme for the FL optimization problem in wireless networks, e ff ectively enhancing FL recognition accuracy.”
From data heterogeneity to convergence: A data-centric review of federated learning
Nguyen, H. T., Bettinelli, M., Ghaffari, A., Benoît, A., Nguyen, T., Pirttikangas, S., & Lovén, L. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135005 · Cited by 1
Huang, H., Feng, Y., Yuan, J., & Zhang, L. (2026) · IEEE International Conference on Radio Frequency and Antenna Technologies (RFAT) · doi:10.1109/rfat69041.2026.11634063 · Cited by 1
“Although recent studies have employed digital twin-assisted hypernetworks [11] and wireless convergence time optimization strategies [12] to enhance system efficiency, these approaches lack resilience mechanisms and often overlook critical hardware failures.”
Titouni, S., Messaoudene, I., Hedir, A., & Djeffal, N. (2026) · Applied Sciences · doi:10.3390/app16168130 · Cited by 1
User-centric User Selection for Federated Learning in Visible-Light Networks
Li, X., Peng, M., Yang, H., & Zhang, H. (2021) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc52777.2021.9580327 · Cited by 1
Resource Optimization for Wireless Federated Learning
Hong, C. S., Khan, L. U., Chen, M., Chen, D., Saad, W., & Han, Z. (2021) · Wireless networks · doi:10.1007/978-981-16-4963-9_3 · Cited by 1
Self-citationOptimal Routing for Stream Learning Systems
Fu, X., & Modiano, E. (2022) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom48880.2022.9796959 · Cited by 1
“…learning systems (where the training data is stored in a central memory and can be accessed by all computation nodes [15], [16], [17], and federated learning systems, where the training data is stored in the local memory of of each node and can be accessed on demand [18], [19], [20], [21].”
BackgroundWireless Time-Triggered Federated Learning with Adaptive Local Training Optimization
Zhou, X., Deng, Y., Xia, H., & Wu, S. (2023) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps57453.2023.10226087 · Cited by 1
“In [8, 9], authors considered constrained training time budget, and jointly designed the user scheduling and resource allocation scheme accordingly.”
BackgroundLi, L., Lv, Y., Sun, B., Wang, M., Chen, B., Li, Z., & Fan, H. (2024) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-247173 · Cited by 1
“The base station prefers to include the local model of all users to generate a converged global model [13].”
Shi, L., Ren, Y., Xu, J., Xie, Y., Chen, F., & Fan, Y. (2025) · Computing · doi:10.1007/s00607-025-01418-x · Cited by 1
“In [29, 30], the authors investigated joint user selection and resource allocation to enhance performance in FL.”
Revisiting Communication-Efficient Federated Learning with Balanced Global and Local UpdatesPreprint
Yan, Z., Li, D., Zhang, Z., & He, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.01470 · Cited by 1
“However, the optimal solutions were only evaluated numerically in [22], [23], and there are no closed-form expressions to facilitate the analyses.”
BackgroundTowards Scalable and Secure Federated Learning: Key Issues and Future ResearchPreprint
Daniels, M., Gallus, S., & Wood, R. (2025) · doi:10.36227/techrxiv.173894842.25024919/v1 · Cited by 1
Efficient Federated Learning over Wireless Networks
Chen, Z. (2024) · Queen Mary Research Online (Queen Mary University of London) · Cited by 1
Distributed Learning for 5G and Beyond Network Management and Orchestration
Sana, M. (2021) · theses.fr (ABES) · doi:10.70675/0f4e2d38zaf10z472bz98caz8ad6e228b6c8 · Cited by 1
Jin, R. (2020) · NCSU Libraries Repository (North Carolina State University Libraries)
Joint Communication, Control, and Learning for Connected and Autonomous Vehicles
Zeng, T. (2021) · VTechWorks (Virginia Tech)
2021 Index IEEE Transactions on Wireless Communications Vol. 20
(2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3135649
Resource allocation for federated learning enabled edge intelligence
Lim, B. W. Y. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/156418
Energy-Efficient Federated Learning in IoT Networks
Kong, D., You, Z., Chen, Q., Wang, J., Hu, J., Xiong, Y., & Wu, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-97774-0_3
Hyperparameter Free MEE-FP based Learning for Next Generation Communication SystemsPreprint
MItra, R., Kaddoum, G., & da Costa, D. B. (2021) · doi:10.36227/techrxiv.16640035
Hyperparameter Free MEE-FP based Learning for Next Generation Communication SystemsPreprint
Mitra, R., Kaddoum, G., & da Costa, D. B. (2021) · doi:10.36227/techrxiv.16640035.v1
“In existing works, several emerging DL paradigms, such as federated-learning [5], meta-learning for low-pilot training [6], reinforcement-learning [7], are derived for several of the relevant sub-tasks of the next-generation communication systems [1].”
BackgroundAdaptive Federated Learning for Battery-powered IIoT Devices with Non-IID Data
Wu, J., Fan, S., Tian, H., & Wu, H. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118938
“and the computing delay is given by [9]”
BackgroundMethodInfluentialClient Selection Based on Diversity Scaling for Federated Learning on Non-IID Data
Ren, Y., Sajjanhar, A., Gao, S., & Loke, S. W. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-40467-2_8
Network optimization for distributed machine learning over networks
Liu, Y. (2023) · Digital Repository Service (Northeastern University) · doi:10.17760/d20621564
Zhongtian, 杜. D., Wuwei, 黄. H., & Yang, 杨. Y. (2024) · Laser & Optoelectronics Progress · doi:10.3788/lop232054
Gau, R.-H., Wang, T., & Liu, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.09076
“The convergence of a synchronized federated learning process has been extensively studied in the literature [11] [12].”
BackgroundMethodA Vehicles Scheduling Algorithm Based on Clustering Based Federated Learning
Zhang, X., Zhang, C., Liu, S., & Jin, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-4566-4_26
Application of All Members-Based Optimizer Algorithm With Federated Learning in VANETS
Yogi, M. K., & Radhika, V. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-0265-2.ch010
Ahamed, B. B., Manoharan, M., Sherubha, P., & Sasirekha, S. P. (2025) · Research Square · doi:10.21203/rs.3.rs-5966493/v1
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.