Energy Efficient Federated Learning Over Wireless Communication Networks
Open accessThe DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Abstract
In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the system under a latency constraint. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. Since the iterative algorithm requires an initial feasible solution, we construct the completion time minimization problem and a bisection-based algorithm is proposed to obtain the optimal solution, which is a feasible solution to the original energy minimization problem. Numerical results show that the proposed al…
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
“For example, FL has facilitated smart health services by enabling machine learning (ML) modeling without sharing patient data across multiple medical institutions [9].”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [9]
In the citing paper
“Both computation energy consumption for local model updates and communication energy consumption for uploading local updates are simultaneously minimized in [92] by considering the learning latency and accuracy constraints for wireless FL.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [92]
In the citing paper
“The constraint of power in IoT devices is a major issue for the deployment of federated learning.”
From Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis (2021) · cites this paper as [17]
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 1×
“federated learning (FL) framework that will be adopted in future Internet of Things (IoT) systems [16]–[24].”
BackgroundA 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×
“To this end, distributed learning frameworks are needed, to enable the wireless devices to collaboratively build a shared learning model with training their collected data locally [6]–[15].”
BackgroundSelf-citationOn Nonlinear Fractional Programming
Dinkelbach, W. (1967) · Management Science · doi:10.1287/mnsc.13.7.492 · Cited by 3,139
Towards 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 · cited 1×
“INTRODUCTION In future wireless systems, due to privacy constraints and limited communication resources for data transmission, it is impractical for all wireless devices to transmit all of their collected data to a data center that can use the collected data to implement centralized machine learning algorithms for dat…”
BackgroundAdaptive 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 FL training problem can be formulated as [2], [19], [25]:”
BackgroundClient Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761315 · Cited by 1,875
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2018) · arXiv · doi:10.48550/arxiv.1804.08333 · Cited by 1,875
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734 · cited 1×
“To this end, distributed learning frameworks are needed, to enable the wireless devices to collaboratively build a shared learning model with training their collected data locally [6]–[15].”
BackgroundDynamic computation offloading for mobile-edge computing with energy harvesting devices
Mao, Y., Zhang, J., & Letaief, K. B. (2016) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2016.2611964 · Cited by 1,705 · cited 2×
“The effective switched capacitance in local computation is κ = 10−28 [35].”
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 5×
“In FL, wireless devices can cooperatively execute a learning task by only uploading local learning model to the base station (BS) instead of sharing the entirety of their training data [25].”
BackgroundMethodInfluential
Research works printed but not linked: 1
- lin, 2018, Don’t use large mini-batches, use local SGD, arXiv 1808 07217
Cited by
Items 901–1,000 of 1,002
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
MG2FL: Multi-Granularity Grouping-Based Federated Learning in Green Edge Computing Systems
Dai, Z., Zhao, Y., Qiu, C., Wang, X., & Yu, F. R. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437153 · Cited by 3
“Some papers have focused on reducing FL energy consumption, such as Yang et al. in [7] proposed an iterative algorithm to minimize the total energy consumption of local computation and wireless transmission.”
BackgroundZhu, C., Sui, M., Zhao, H., Chen, K., Zhang, T., & Bao, C. (2024) · Electronics · doi:10.3390/electronics13061129 · Cited by 3
Federated Learning Convergence Optimization for Energy-Limited and Social-Aware Edge Nodes
Ling, X., Chi, W., Zhang, J., & Li, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3438163 · Cited by 3
Du, H., & Yang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70362-1_8 · Cited by 3
Self-citationF2NAS: Flexible Federated Neural Architecture Search in Green Edge Computing
Zhao, Z., Qiu, C., Zhao, Y., Wang, X., Yao, H., Li, X., & Yu, F. R. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10623100 · Cited by 3
“In F²NAS , the substantial computation and interaction with the cloud lead to the highest energy consumption for the architecture [18].”
BackgroundA Novel Extended-Kalman-Filter-Incorporated Latent Feature Model on Dynamic Weighted Directed Graphs
Zhou, H., Chen, X., & Yuan, Y. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10832044 · Cited by 3
“A dynamic weighted directed graph (DWDG) is a mathematical abstraction that represents a system of entities and the evolving relationships between them over time [1-6].”
Knowledge and Model-Driven Deep Reinforcement Learning for Federated Edge Learning
Li, Y., Zhao, L., & Yang, F. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901314 · Cited by 3
Resource Allocation for Federated Learning With Highly Distorted Model
Ryu, J.-W., Tung, N. X., Nguyen, M.-D., Vinh, Q., & Hwang, W.-J. (2025) · IEEE Access · doi:10.1109/access.2025.3556780 · Cited by 3
Improving Wireless Federated Learning via Joint Downlink-Uplink Beamforming Over Analog Transmission
Zhang, C., Dong, M., Liang, B., Afana, A., & Ahmed, Y. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3595700 · Cited by 3
Scheduling and Fusion for Multimodal Federated Learning in Energy-Constrained Wireless Networks
Zheng, J., Yu, J., & Liu, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3615129 · Cited by 3
Requirements for Using Federated Learning in Manufacturing Supply Chains
Kallisch, J., & Gómez, J. M. (2025) · Intelligent systems reference library · doi:10.1007/978-3-032-06889-7_3 · Cited by 3
Unequal error protection transmission for federated learning
Zheng, S., & Chen, X. (2022) · IET Communications · doi:10.1049/cmu2.12379 · Cited by 3
Synchronizing tasks for distributed learning in connected and autonomous vehicles
Subedi, P., Yang, B., & Hong, X. (2022) · Journal of Communications and Networks · doi:10.23919/jcn.2022.000028 · Cited by 3
Energy Efficient Wireless Crowd Labeling: Joint Annotator Clustering and Power Control
Li, X., Zhu, G., Shen, K., Han, K., Huang, K., & Gong, Y. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3208198 · Cited by 3
“To achieve energy efficient EL, the communication and computation resource allocations were jointly optimized in [36] and [37].”
MethodHeterogeneous 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
“Existing works in FL have focused on improving model accuracy [10] or reducing energy cost [11], usually with a random client selection algorithm.”
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
“2) Uplink Transmission: Each selected edge device n uploads its model difference to the edge server via frequency division multiple access (FDMA) [11].”
BackgroundInfluentialJia, G., Kong, B., Yang, L., Zhang, Y., Zeng, J., Li, C., Zhu, Y., & Zhang, J. (2023) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops57953.2023.10283723 · Cited by 3
“Traffic Engineering (TE) is widely applied to wide area networks (WANs) and optimises traffic performance, network reliability as well as resource allocation [1].”
BackgroundBandwidth Allocation for Low-Latency Wireless Federated Learning: An Evolutionary Game Approach
Zhang, S., Xu, Y., Liu, J., Takakura, H., Chen, L., & Shiratori, N. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279623 · Cited by 3
Qian, L., Li, M., Dong, X., Wu, Y., & Yang, X. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278703 · Cited by 3
Contention Matters: Modeling and Analyzing the Performance of Federated Learning over WiFi
Kukreja, P., & Mahendran, V. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293805 · Cited by 3
“…the state of the art approaches can be broadly classified into two categories as follows: 1) Improvement in the communication layer: By tuning communication resources such as varying transmission power [4], or by varying both transmission power and allocating bandwidth to different clients [5].”
BackgroundHeterogeneity-Aware Federated Learning with Adaptive Local Epoch Size in Edge Computing
Yao, W., Liu, T., Cui, Y., & Zhu, Y. (2023) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn60784.2023.00036 · Cited by 3
Optimized Edge Aggregation for Hierarchical Federated Learning
Xu, B., Xia, W., Wen, W., Zhao, H., & Zhu, H. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625432 · Cited by 3
Data Caching at Fog Nodes Under IoT Networks: Review of Machine Learning ApproachesPreprint
Tapwal, R., Gupta, N., & Xin, Q. (2020) · doi:10.36227/techrxiv.12091410.v1 · Cited by 3
Data Caching at Fog Nodes Under IoT Networks: Review of Machine Learning ApproachesPreprint
Tapwal, R., Gupta, N., & Xin, Q. (2020) · doi:10.36227/techrxiv.12091410 · Cited by 3
Al-Abiad, M. S., Obeed, M., Hossain, M. J., & Chaaban, A. (2022) · doi:10.36227/techrxiv.19740394 · Cited by 3
Energy-efficient Federated Learning for UAV CommunicationsPreprint
Fu, C.-W., & Ku, M.-L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.03171 · Cited by 3
“3 compares the following baseline methods: (1) random participation [21], where two UEs are randomly selected per time slot; and (2) fixed participation [15], where all UEs participate in every time slot.”
Efficient Spectral Efficiency Maximization Design for IRS-aided MIMO SystemsPreprint
Li, F., Wang, Y., Lian, Z., & Chen, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.26279 · Cited by 3
Omeke, K. G., Mollel, M. S., Zhang, L., Abbasi, Q. H., & Imran, M. A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.24648 · Cited by 3
“Receive energy is , where Φ i is the number of floating-point operations (FLOPs) and ϵ op is the energy per operation [35].”
On Developing Sustainable Deep Learning Applications Using Pre-calculating Energy Usage
Puangpontip, S., & Hewett, R. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-37470-8_2 · Cited by 2
Knowledge Caching for Federated Learning in Wireless Cellular Networks
Zheng, X., Lee, M., Hsu, K., & Hong, Y.-W. P. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3360642 · Cited by 2
“Specifically, [11] proposed a resource allocation policy to minimize the communication cost of the FL process while providing a training performance guarantee; and [12] considered a similar problem where physical layer designs were proposed for both the uplink and the downlink.”
BackgroundProvision for Energy: A Resource Allocation Problem in Federated Learning for Edge Systems
Liu, M., Rajamanickam, L., & Parthasarathy, R. (2024) · EAI Endorsed Transactions on Energy Web · doi:10.4108/ew.6503 · Cited by 2
Debiased Device Sampling for Federated Edge Learning in Wireless Networks
Chen, S., Li, Q., Shi, Y., & Li, X. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3464740 · Cited by 2
A Biological Structure-Inspired Infrastructure Health Assessment Method
Zhang, M., Li, G., He, B., Zhang, D., Tian, Y. C., & Cheng, B. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3510466 · Cited by 2
“Conversely, six nodes demonstrate first-order dominance, positioned at coordinates [ 1 , 6 ] , [ 5 , 7 ] , [ 5 , 9 ] , [ 1 , 11 ] , [ 0 , 19 ] , and [ 3 , 17 ] .”
Energy-efficient Federated Learning with Dynamic Model Size Allocation
Kumar, M. S. C., Sai Satya Narayana, J., Bao, Y., Wang, X., & Drew, S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825664 · Cited by 2
“As a result, there is a notable rise in overall energy use and related emissions [3, 4].”
An Overview of Wireless Communication Protocols and Techniques for Drones
Sodha, P., & Kumar, A. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-97-5621-6_29 · Cited by 2
Hyperdimensional Computing Empowered Federated Foundation Model over Wireless Networks for Metaverse
Ding, Y., Shang, W., Xu, M., Yang, Z., Hu, Y., Niyato, D. T., & Shikh‐Bahaei, M. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00334 · Cited by 2
“…the optimization process, we consider this is a synchronous system, in other words, the users are to start transmitting sample HVs at the same time [13], and the optimization problem is formulated as follows: P1: where the problem objective in (10a) aims to minimize the maximum transmission…”
Self-citationChen, S., Huang, S., Zhou, Z., Li, X., Yang, S., Sun, Y., & Xu, C. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978262 · Cited by 2
“To provide convergence conditions for SGD, we introduce the definition of local accuracy σ that characterizes the quality of the local solution, and the output ∆ θ tn satisfies [12]: where G is the objective optimization function to the local clients.”
GenFV: AIGC-Assisted Federated Learning for Vehicular Edge Intelligence
Qiang, X., Chang, Z., & Kliks, A. (2025) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit63408.2025.11037154 · Cited by 2
Federated Machine Learning Solutions: A Systematic Review
Samuel, A., & Edegbe, G. N. (2025) · NIPES Journal of Science and Technology Research · doi:10.37933/nipes/7.3.2025.4 · Cited by 2
Contrastive Reinforcement Learning for Adaptive Client Selection in Federated Learning
Zhang, J., Wang, H., Li, F., Li, J., Zhou, N., & Li, Q. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.07.137 · Cited by 2
Intelligent Frameworks for Minimizing Job Completion Time in Clustered Federated Learning
Yu, J., Zhou, R., Li, B., & Wu, L. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3600674 · Cited by 2
Zhao, J., Chen, M., Le, M., Huang, M., Yang, Z., & Pham, Q. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161520 · Cited by 2
“In our considered S2FL network, we adopt frequency division multiple access (FDMA) to enable asynchronous transmissions [10].”
Self-citationIftikhar, S., Khan, H. A., & Davy, S. (2025) · Frontiers in artificial intelligence and applications · doi:10.3233/faia251355 · Cited by 2
Optimizing Client Participation in Communication-Constrained Federated LLM Adaptation with LoRA
Solat, F., & Lee, J. (2025) · Sensors · doi:10.3390/s25216538 · Cited by 2
“Similar efficiency ratios have been employed in prior work on resource-aware FL [18,19].”
UAV-RIS Enhanced Wireless Power Transfer for Urban IoT Networks
Kadhim, M. A., & Thabit, A. A. (2025) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2025.10.011 · Cited by 2
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
Self-citationZhang, X., Deng, Y., & Mahmoodi, T. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3707692 · Cited by 2
“…by analyzing the entire global iteration process, which is divided into four main steps: 1) Local Model Update With Pruning: When the u -th m tier local model receives the model parameters from the k -th round of global aggregation, it prunes the model using a pruning mask as the pruning operation.”
Energy-Efficient Federated Learning With Relay-Assisted Aggregation in IIoT Networks
Hashempour, H. R., Nozari, M., Berardinelli, G., Li, Y., Zhang, J., Ngo, H. Q., & Pandey, S. R. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3696125 · Cited by 2
“2, the time required to complete one round of the FL process, denoted by T t , consists of two main components: the local computation time and the UL transmission time.”
Niu, J., Zhou, H., An, Y., Zhang, S., & Chi, K. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3646068 · Cited by 2
Optimizing Energy Efficiency for Federated Learning in Rotary-Wing UAV Air-to-Ground Communications
Dang, X.-T., Nguyen, Q.-S., & Shin, O.-S. (2025) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2025.3599309 · Cited by 2
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
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
Self-citationMihertie, H. D., Zhengqiang, W. A. N. G., Jain, D. K., & Li, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3648443 · Cited by 2
EcoFL: Resource Allocation for Energy-Efficient Federated Learning in Multi-RAT ORAN Networks
Salama, A., Qazzaz, M. M. H., Shah, S. D. A., Hafeez, M., Zaidi, S. A. R., & Ahmadi, H. (2025) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom65874.2025.11313364 · Cited by 2
“In contrast, Yang et al. [9] incorporate latency constraints to minimise device energy consumption.”
Scheduling and Resource Allocation for Federated Learning in Vehicular Networks
Heydari, M., Todd, T. D., Zhao, D., & Karakostas, G. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11309961 · Cited by 2
Adaptive Quantization and Differential Privacy Federated Learning Framework
Nguyen, M. H., Nguyen, C.-H., Nguyen, D. N., Hoang, D. T., & Alsheikh, M. A. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3665886 · Cited by 2
Latency and Energy Minimization in RIS-Enabled AirComp Federated Learning Networks
Charatsaris, P., Voikos, S., Diamanti, M., & Papavassiliou, S. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3667419 · Cited by 2
Chen, R., Wan, Q., Zhang, X. D., Qin, X., Hou, Y., Wang, D., Fu, X., & Pan, M. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3671076 · Cited by 2
Energy-efficient DDPG-based Federated Learning-assisted Fluid Antenna Systems with MC-NOMA
Ho, M. C., & Cho, S. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432285 · Cited by 2
“As a result, the aggregation time for local model updates at the server, as well as the downlink transmission time, are considered negligible in comparison to the local computation time at the user devices and the uplink transmission time [7].”
Empowering UAV intelligence with multi-cell federated learning under wireless packet error
Jing, Y., Qu, Y., Chao, D. O. N. G., Wu, T., & Qihui, W. U. (2026) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2026.104213 · Cited by 2
Haider, G., Kundroo, M., Zhang, L., Choi, J., & Kim, T. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103813 · Cited by 2
Generative AI with federated learning
Yao, Z., Yang, D., & Wang, Y. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-341497-8.00022-5 · Cited by 2
Time is Gold: A Time-Dependent Incentive Mechanism Design for Fast Federated Learning
Ling, X., Li, R., Ouyang, T., & Chen, X. (2022) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc55456.2022.9880744 · Cited by 2
“[6] considered a slightly different problem.”
WFLTree: A Spanning Tree Construction for Federated Learning in Wireless Networks
Li, S., Zheng, Y., & Zou, Y. (2023) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126623502201 · Cited by 2
VersatileFL: Volatility-Resilient Federated Learning in Wireless Edge Networks
Yoon, J., Kim, J., Byeon, Y., & Lee, H. (2023) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon58729.2023.10287447 · Cited by 2
Semantic Feature-Based Learning Framework for Energy-Limited Semantic Communication System
Fang, Z., Sun, M., Wang, Y., & Xu, X. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10571281 · Cited by 2
“6 log 10 ( d ) , where d is the distance from the edge server to the device in kilometers, and the standard deviation of shadow fading is set to 8 dB [12].”
BackgroundCP2GFed: Cross-granular and Personalized Prompt-based Green Federated Tuning for Giant Models
Gao, F., Zhao, Y., Qiu, C., Wang, X., Yao, H., & Hu, Q. (2024) · International Workshop on Quality of Service · doi:10.1109/iwqos61813.2024.10682866 · Cited by 2
“Yang et al. [20] propose an iterative algorithm to reduce the energy consumption (i.e., the local computation energy and the wireless transmission energy) under a latency constraint.”
BackgroundMethodLoLaFL: Low-Latency Federated Learning via Forward-only Propagation
Zhang, J., Huang, J., & Huang, K. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162348 · Cited by 2
Resilient Inference for Personalized Federated Learning in Edge Computing Environments
Xiao, K., Wang, Q., Anagnostopoulos, C., & Bryson, K. (2025) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw63273.2025.00021 · Cited by 2
“Then, the energy consumption for data transmission is: Moreover, according to [12], [13], the energy consumption of edge node j for inference computation is formulated as κ (cid:12)(cid:12) D k l,i (cid:12)(cid:12) f 2 j , where κ is the effective switched capacitance depending on the chip architecture.”
InfluentialAn Optimization Framework for Federated Edge Learning
Li, Y., Cui, Y., & Lau, V. K. N. (2022) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51304.2022.9834013 · Cited by 2
Ye, H., Chen, Z., Jia, Y., & Chen, S. (2022) · Entropy · doi:10.3390/e24040537 · Cited by 2
“The authors of [18] investigated the energy transmission and computation resource allocation problem in a federated learning-oriented wireless communication network.”
BackgroundJoint Accuracy and Resource Allocation for Green Federated Learning Networks
Chu, X., Liu, X., Chen, Q., Xiong, Y., Wang, J., Yu, H., & Hu, X. Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-97774-0_14 · Cited by 2
Liu, S., Yu, G., Chen, X., & Bennis, M. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9839164 · Cited by 2
“Owing to the sufficient transmission resource, the latency for both edge and global model broadcasting can be ignored in general [10], [12].”
BackgroundAn 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
Latency and Energy Consumption of Convolutional Neural Network Models from IoT Edge Perspective
Hauschild, S., & Hellbrück, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20936-9_31 · Cited by 2
Joint Source-Channel Coding for Efficient Image Transmission: An Information Bottleneck Based Scheme
Sun, L., Guo, C., & Yang, Y. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008561 · Cited by 2
Semi-Federated Learning for Edge Intelligence with Imperfect SIC
Ni, W., Zheng, J., Eldar, Y. C., You, C., & Huang, K. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095782 · Cited by 2
Deep Learning for 5G and Beyond
Mohamed, K. S. (2023) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-031-35737-4_5 · Cited by 2
Digital twin‐based framework for wireless multimodal interactions over long distance
Kang, M., Li, X., Ji, H., & Zhang, H. (2023) · International Journal of Communication Systems · doi:10.1002/dac.5603 · Cited by 2
“The training reliability is indicated by the model divergence rate ε D ; c ð t Þ , whose relationship with the iteration time I ð t Þ can be derived similar to the derivation in Appendix A in Yang et al 25 by where z is determined by the learning rate and loss function, I ð t Þ is the iteration time.”
MethodOne-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
Convergence Analysis and Optimization of SWIPT-Based Over-the-Air Federated Learning
Fan, S., Tao, S., Ni, W., & Tian, H. (2024) · IEEE Communications Letters · doi:10.1109/lcomm.2024.3371216 · Cited by 2
“F EDERATED learning (FL), a distributed learning architecture, is based on the principle of model sharing rather than raw data uploading, which dramatically decreases communication overhead and latency while also protecting user privacy [1].”
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
“Other energy-efficient frameworks are proposed in [9], [10] where the objective is to minimize the energy consumption for transmission in [9] and for both computation and transmission in [10].”
BackgroundCheng, G., Li, P., Tan, B., Yu, R., Wu, Y., & Pan, M. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3480045 · Cited by 2
Gradient Compensation Enabled Federated Learning for Unreliable Wireless Links
Chen, Z., Yi, W., Kim, Y. H., & Nallanathan, A. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901363 · Cited by 2
Wang, T., Li, P., Feng, P., Wei, X., Qian, L., & Wu, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3569669 · Cited by 2
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
“Recent studies, [3], [4], [5], [6], [7] to name a few, suggest that transitioning from centralized to distributed computing has the potential to reduce the overall energy consumed to train machine learning solutions.”
Joint Optimization of Offloading, Batching and DVFS for Multiuser Co-Inference
Xu, Y., Zhou, S., & Niu, Z. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161748 · Cited by 2
“The corresponding energy consumption for computing is: where κ m represents the effective switched capacitance, depending on the chip architecture of device m [21], and q n reflects differences between blocks.”
Latency-Aware Multimodal Federated Learning Over UAV Networks
Shaon, S., & Nguyen, D. C. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3617948 · Cited by 2
“Following the interior-point method analysis in [32], the resulting per-iteration computational complexity is expressed as O ((4 U ) 2 √ 8 U ) .”
Rethinking Outage in Federated Learning: An Adaptive Retransmission Design
Lin, X., Liu, Y., & Chen, F. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3621847 · Cited by 2
Energy-Aware Federated Learning: Solutions and Challenges
Ravihansa, V., Wang, S., & Liyanage, M. (2025) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses66335.2025.11359841 · Cited by 2
Saddle Point Approximation Based Delay Analysis for Wireless Federated Learning
Yang, L., Li, L., Guo, X., Shi, Y., Wang, H., & Chen, W. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500298 · Cited by 2
“In [11], the upper bound of global iteration is derived under the assumption that the loss function is L-smooth and γ-strongly convex.”
BackgroundPerformance Optimization of Distributed Primal-Dual Algorithms over Wireless Networks
Yang, Z., Chen, M., Wong, K., Saad, W., Poor, H. V., & Cui, S. R. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500853 · Cited by 2
Self-citationResource Consumption for Supporting Federated Learning Enabled Network Edge Intelligence
Liu, Y., Feng, G., Sun, Y., Li, X., Zhou, J., & Qin, S. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814613 · Cited by 2
“To achieve the local and global model accuracy given in the next subsection, we first make the following three assumptions on the loss function Fi(w), as that in [7], [8], • Assumption 1: Function Fi(w) is L-Lipschitz, i.”
BackgroundMethodResultInfluentialLocal Training and Scalability of Federated Learning Systems
Zawad, S., Yan, F., & Anwar, A. (2022) · Springer eBooks · doi:10.1007/978-3-030-96896-0_10 · Cited by 2
Systems Bias in Federated Learning
Zawad, S., Yan, F., & Anwar, A. (2022) · Springer eBooks · doi:10.1007/978-3-030-96896-0_12 · 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
Performance Analysis of Federated Learning in wireless networks
Joomye, A., Tahir, M., Sheikh, M. A., Ling, M. H., & Meng, Y. K. (2022) · IEEE International Symposium on Telecommunication Technologies · doi:10.1109/istt56288.2022.9966534 · Cited by 2
“In [9], the authors propose an algorithm to optimize the energy consumption of the UEs by attempting to minimize computation and transmission energy consumption.”
Evolutionary Edge Association and Auction in Hierarchical Federated Learning
Lim, W. Y. B., Ng, J. S., Xiong, Z., Niyato, D. T., & Miao, C. (2022) · Wireless networks · doi:10.1007/978-3-031-07838-5_4 · Cited by 2
Metadata
- Authors
- Yang, Z., Chen, M., Saad, W., Hong, C. S., & Shikh-Bahaei, M.
- Affiliations
- King's College London (GB)
- Princeton University (US)
- Virginia Tech (US)
- Kyung Hee University (KR)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2021-03
- Volume
- 20
- Issue
- 3
- Pages
- 1935-1949
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W3109847748
- Cited by
- 1,153
- References
- 45
- Citations by year
- 2026: 116 · 2025: 198 · 2024: 241 · 2023: 237 · 2022: 195 · 2021: 115
- FWCI
- 58.63
- 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
- Engineering and Physical Sciences Research Council (EPSRC) through the Scalable Full Duplex Dense Wireless Networks (EP/P003486/1)
- U.S. National Science Foundation (CNS-1814477)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Keywords
- federated learning, energy efficiency, wireless networks, resource allocation, time allocation, bandwidth allocation, power control, learning accuracy, iterative methods, completion time minimization
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.