Opportunities of Federated Learning in Connected, Cooperative, and Automated Industrial Systems
Open accessThe DOI matches its Crossref record; 17 of the 18 references it cites were found in a registry or an index.
Abstract
Next-generation autonomous and networked industrial systems (i.e., robots, vehicles, drones) have driven advances in ultra-reliable low-laten-cy communications (URLLC) and computing. These networked multi-agent systems require fast, communication-efficient, and distributed machine learning (ML) to provide mission-crit-ical control functionalities. Distributed ML techniques, including federated learning (FL), represent a mushrooming multidisciplinary research area weaving together sensing, communication, and learning. FL enables continual model training in distributed wireless systems: rather than fusing raw data samples at a centralized server, FL leverages a cooperative fusion approach where networked agents, connected via URLLC, act as distributed learners that periodically exchange their locally trained model parameters. This article explores emerging opportunities of FL for the next-generation networked industrial systems. Open problems are discussed, focusing on cooperative driving in connected automated vehicles and collaborative robotics in smart manufacturing.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It can also overcome the straggler dilemma with heterogeneous hardware, as well as improve the robustness to data poisoning attacks and master node fails [35], [145].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [145]
Experimental — accuracy not yet measuredIn the citing paper
“It has great potentials for applications in the autonomous industrial systems, including cooperative automated driving, cooperative simultaneous localization and mapping, and collaborative robotics in advanced manufacturing environments [145].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [145]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Self-citationAdaptive 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×
“allocation has been considered to find the best trade-off between on-device computation (SGD updates) and wireless channel use for parameters exchange [10].”
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 2×
“averaging [2], alternates between the computation of a local model at each device and a round of communication with the server for learning of a global model.”
BackgroundMethodUltrareliable and Low-Latency Wireless Communication: Tail, Risk, and Scale
Bennis, M., Debbah, M. A., & Poor, H. V. (2018) · Proceedings of the IEEE · doi:10.1109/jproc.2018.2867029 · Cited by 1,048
Self-citationBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2020) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2921755 · Cited by 887 · cited 1×
“In addition to the above tools, distributed ledger technologies can also be applied to decentralized training [11] by validating clients model updates via a series of validation steps (Proof-of-Work, or others).”
Self-citationBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1808.03949 · Cited by 882 · cited 1×
“In addition to the above tools, distributed ledger technologies can also be applied to decentralized training [11] by validating clients model updates via a series of validation steps (Proof-of-Work, or others).”
Self-citationFederated Learning Over Wireless Fading Channels
Amiri, M. M., & Gunduz, D. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.2974748 · Cited by 625 · cited 2×
“More recently, analog FL and hybrid analog-digital implementations have been proposed for fast and synchronous model averaging [4].”
MethodSayed, A. H., Tu, S.-Y., Chen, J., Zhao, X., & Towfic, Z. J. (2013) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2231991 · Cited by 494 · cited 3×
“On-device optimization (t = 3) finally adjusts the local model by combining the gradients obtained from local loss with those received from the neighbor (combine-and-adapt [7]).”
BackgroundMethodFederated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks
Savazzi, S., Nicoli, M., & Rampa, V. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2964162 · Cited by 431 · cited 6×
“Decentralized FL techniques [6] are promising solutions for”
BackgroundInfluentialSelf-citationDecentralized Federated Learning via SGD over Wireless D2D Networks
Xing, H., Simeone, O., & Bi, S. (2020) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc48557.2020.9154332 · Cited by 122
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“2) Ultra-Reliable and Low-Latency Communication: The packet length of the extracted output features transmitted from the edge devices can be very short [83], [145], for which the achievable data rate in such a finite block length regime is penalized by a non-vanishing decoding error probability [83].”
BackgroundInfluentialDecentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges
Martínez Beltrán, E. T., Pérez, M. Q., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3315746 · Cited by 625
“In [8], the authors discussed the opportunities and applications of DFL in automated and networked industrial systems supported by Device-to-Device (D2D) communications.”
BackgroundMethodDecentralized Federated Learning: A Survey and Perspective
Yuan, L., Wang, Z., Sun, L., Yu, P. S., & Brinton, C. G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3407584 · Cited by 290
“DFL has received extensive attention as an emerging framework [55], [56], [57], [58], [59], [60].”
BackgroundFederated learning for smart cities: A comprehensive survey
Pandya, S., Srivastava, G., Jhaveri, R., Babu, M. R., Bhattacharya, S., Maddikunta, P. K. R., Mastorakis, S., Piran, M. J., & Gadekallu, T. R. (2023) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2022.102987 · Cited by 297
Chellapandi, V. P., Yuan, L., Brinton, C. G., Żak, S. H., & Wang, Z. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3332675 · Cited by 236
Autonomous vehicles in 5G and beyond: A survey
Hakak, S., Gadekallu, T. R., Maddikunta, P. K. R., Ramu, S. P., M, P., De Alwis, C., & Liyanage, M. (2023) · Vehicular Communications · doi:10.1016/j.vehcom.2022.100551 · Cited by 228
Collaborative Sensing in Internet of Things: A Comprehensive Survey
He, S., Shi, K., Liu, C., Guo, B., Chen, J., & Shi, Z. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3187138 · Cited by 223
“Besides, the authors in [104] summarize system deployment and potential opportunities of federated sensing in IWSNs.”
BackgroundA Comprehensive Survey of V2X Cybersecurity Mechanisms and Future Research Paths
Sedar, R., Kalalas, C., Vazquez-Gallego, F., Alonso, L., & Alonso-Zarate, J. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3239115 · Cited by 159
Decentralized Federated Learning for Healthcare Networks: A Case Study on Tumor Segmentation
Camajori Tedeschini, B., Savazzi, S., Stoklasa, R., Barbieri, L., Stathopoulos, I., Nicoli, M., & Serio, L. (2022) · IEEE Access · doi:10.1109/access.2022.3141913 · Cited by 164
“Fully decentralized FL policies have been considered for training on low-power devices (robots, drones) in several industrial verticals [15], [33] such as robotics, connected automated vehicles [14], [34] and medical diagnosis [35].”
BackgroundSelf-citationBhavsar, M., Bekele, Y. B., Roy, K., Kelly, J. C., & Limbrick, D. B. (2024) · IEEE Access · doi:10.1109/access.2024.3386631 · Cited by 203
“V2X communication enables vehicles to share relevant data and cooperate, enhancing overall traffic efficiency and safety [19].”
BackgroundTallat, R., Hawbani, A., Wang, X., Al‐Dubai, A., Zhao, L., Liu, Z., Min, G., Zomaya, A. Y., & Alsamhi, S. H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3329472 · Cited by 196
“Typical FL designs, for instance, disregard the structure and dynamics of the network graph, the prevalence of sporadic communication links, and weakly connected components [310].”
BackgroundFederated Neural Architecture Search for Medical Data Security
Liu, X., Zhao, J., Li, J., Cao, B., & Lv, Z. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3144016 · Cited by 165
Applications of Federated Learning; Taxonomy, Challenges, and Research Trends
Shaheen, M., Farooq, M. S., Umer, T., & Kim, B.-S. (2022) · Electronics · doi:10.3390/electronics11040670 · Cited by 157
Over-the-Air Computation for 6G: Foundations, Technologies, and Applications
Wang, Z., Zhao, Y., Zhou, Y., Shi, Y., Jiang, C., & Letaief, K. B. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3405448 · Cited by 165
“In some application scenarios, e.g., cooperative autonomous vehicles and swarm robotics, the behaviors of devices are characterized by time-sensitive functions, which require the corresponding function computation to be finished within ultra-low latency [101].”
BackgroundDrones’ Edge Intelligence Over Smart Environments in B5G: Blockchain and Federated Learning Synergy
Alsamhi, S. H., Almalki, F. A., Afghah, F., Hawbani, A., Shvetsov, A. V., Lee, B., & Song, H. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3132561 · Cited by 139
“The authors of [55] explored FL opportunities for Industry 4.0 networks and collaboration of smart components in smart manufacturing.”
InfluentialLocalization as a Key Enabler of 6G Wireless Systems: A Comprehensive Survey and an Outlook
Trevlakis, S. E., Boulogeorgos, A. A., Pliatsios, D., Querol, J., Ntontin, K., Sarigiannidis, P. G., Chatzinotas, S., & Renzo, M. D. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3324952 · Cited by 158
Italiano, L., Tedeschini, B. C., Brambilla, M., Huang, H., Nicoli, M., & Wymeersch, H. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3449031 · Cited by 151
“𝑖, reply = 𝑡 2 − 𝑡 1 and included in the 𝑖 𝑖 𝑖 ′ ′ ′ ( Δ 𝜙 𝑖 , Δ 𝜒 𝑖 , Δ 𝜓 ) the orientation of the array, where Δ 𝜙 𝑖 , Δ 𝜒 𝑖 Δ 𝜓 𝑖 Δ 𝑖 = 0), the AOA measurement ∠ ( 𝒖 ′ − 𝒔 ′ ) extracted by the antenna array is rotated through a rotation matrix 𝑹 𝑥𝑧 ′ ′ 𝑖 𝑖 where 𝑛 𝑖”
Self-citationFusionFedBlock: Fusion of blockchain and federated learning to preserve privacy in industry 5.0
Singh, S. K., Yang, L. T., & Park, J. H. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.027 · Cited by 115
Decentralized federated learning for extended sensing in 6G connected vehicles
Barbieri, L., Savazzi, S., Brambilla, M., & Nicoli, M. (2021) · Vehicular Communications · doi:10.1016/j.vehcom.2021.100396 · Cited by 137
Self-citationAn Energy and Carbon Footprint Analysis of Distributed and Federated Learning
Savazzi, S., Rampa, V., Kianoush, S., & Bennis, M. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3186439 · Cited by 133
“FL distributes the computing tasks across many devices characterized by low-power consumption profiles, compared with data centers, and each device has access to small datasets [2] only.”
BackgroundSelf-citationFederated Learning via Unmanned Aerial Vehicle
Fu, M., Shi, Y., & Zhou, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3303492 · Cited by 105
“Since only model parameters rather than raw data are exchanged between devices and the PS, FL significantly relieves the communication burden and protects data privacy [4], [6] with wide-field applications, e.g., vehicle-to-vehicle communications [7] and content recommendations for smartphones [5].”
BackgroundQiao, C., Li, M., Liu, Y., & Tian, Z. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3399612 · Cited by 109
“For this benefit, it is used in various recommendation systems, including content recommendations, mobile task recommendations and autonomous driving strategy recommendations [258], [259], [260].”
Federated learning-empowered smart manufacturing and product lifecycle management: A review
Leng, J., Li, R. C., Xie, J., Zhou, X., Li, X., Liu, Q., Chen, X., Shen, W., & Wang, L. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103179 · Cited by 101
Federated learning for big data: A survey on opportunities, applications, and future directions
Gadekallu, T. R., Pham, Q., Huynh‐The, T., Feng, H., Fang, K., Pandya, S., Liyanage, M., Wang, W. W., & Nguyen, T. T. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113614 · Cited by 92
Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification
Wang, S., Li, C., Ng, D. W. K., Eldar, Y. C., Poor, H. V., Hao, Q., & Xu, C. (2023) · IEEE Network · doi:10.1109/mnet.104.2100403 · Cited by 83
“In this case, sensor data is inherently distributed at customers’ vehicles and contains high-resolution human-related private information, leading to the potential of sensitive information leakage [2].”
BackgroundInfluentialFederated Learning in Robotic and Autonomous Systems
Xianjia, Y., Queralta, J. P., Heikkonen, J., & Westerlund, T. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.07.041 · Cited by 79
“On account of features ranging from privacy preservation, decentralized reliability, minimal communication and focus on on-board computation, it is arguable that federated learning has potential to be a secure and efficient robot learning framework in and it will be further adopted across different types of autonomous…”
Luo, S., Xiao, Y., & Song, L. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557668 · Cited by 113
“This new distributed learning paradigm has found applications in content recommendations [1, 15], mobile crowdsourcing task recommendations [7, 19], and autonomous driving strategy recommendations [14].”
BackgroundA Survey of Federated Learning for Connected and Automated Vehicles
Chellapandi, V. P., Yuan, L., Żak, S. H., & Wang, Z. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421974 · Cited by 75
“Recent efforts have been conducted to understand the applicability and challenges of implementing FL to CAVs [11]– [15].”
Xu, Z., Wang, Y., Wu, Z., Zheng, W. X., & Hu, C. X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3540643 · Cited by 83
“Thus, FL frameworks are applicable to many distributed systems, such as IIoT [1], [9] and NNSs [10], as shown in Fig.”
Artificial Intelligence in Industry 4.0: A Review of Integration Challenges for Industrial Systems
Windmann, A., Wittenberg, P., Schieseck, M., & Niggemann, O. (2024) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin58382.2024.10774364 · Cited by 82
“Various strategies have been proposed to mitigate these issues, including synthetic data generation through simulations [64], [65] and federated learning [66], [67], which allows for the utilization of data across decentralized systems while managing privacy concerns.”
Networking Based ISAC Hardware Testbed and Performance Evaluation
Ji, K., Zhang, Q., Wei, Z., Feng, Z., & Zhang, P. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.005.2200440 · Cited by 62
Over-the-Air Decentralized Federated Learning
Shi, Y., Zhou, Y., & Shi, Y. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9517780 · Cited by 67
Chen, J., Wang, E. Z., Srivastava, G., Alghamdi, T. A., Khan, F., Kumari, S., & Xiong, H. (2024) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2024.100593 · Cited by 66
UAV Aided Over-the-Air Computation
Fu, M., Zhou, Y., Shi, Y., Chen, W., & Zhang, R. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3134327 · Cited by 62
Federated learning design and functional models: survey
Ayeelyan, J., Utomo, S., Rouniyar, A., Hsu, H.-C., & Hsiung, P. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10969-y · Cited by 70
“The authors of [148, 149] presented the future industrial uses with respect to federated learning.”
Baker, T., Asim, M., Samwini, H., Shamim, N., Alani, M. M., & Buyya, R. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108676 · Cited by 62
“Similarly, [17] provides a discussion about the use of FL in many B5G use cases including intelligent transportation system.”
BackgroundAlsharif, M. H., Kannadasan, R., Wei, W., Nisar, K. S., & Abdel‐Aty, A. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101251 · Cited by 64
Hagos, D. H., & Rawat, D. B. (2022) · Sensors · doi:10.3390/s22249916 · Cited by 68
“Given the distinctive advantages such as privacy preservation, decentralized learning, parallel training, and onboard processing, FL has the potential to be a secure and efficient AI framework for distributed autonomous systems [75].”
BackgroundPerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Training
Luo, S., Xiao, Y., Zhang, X., Liu, Y., Ding, W., & Song, L. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3664927 · Cited by 65
“This paradigm has found diverse applications in various areas, such as content recommendations [1, 45], mobile crowdsourcing task recommendations [16, 67], and autonomous driving strategy recommendations [43].”
BackgroundDeep data plane programming and AI for zero-trust self-driven networking in beyond 5G
Hireche, O., Benzaïd, C., & Taleb, T. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108668 · Cited by 61
“To mitigate the aforementioned issues, recent research works have been investigating the decentralization of the FL process to enable the aggregation of model updates in a distributed way; that is without requiring a central server [3,46,47].”
BackgroundKokkonen, H., Lovén, L., Motlagh, N. H., Kumar, A., Partala, J., Nguyen, T., Pujol, V. C., Kostakos, P., Leppänen, T., González-Gil, A., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.01423 · Cited by 62
“The purpose is to increase the information flow and speed up the convergence by utilizing also neighbours’ local data, even though these approaches lead to increased communication costs [151].”
BackgroundSelf-citationFederal learning edge network based sentiment analysis combating global COVID-19
Liang, W., Chen, X., Huang, S., Xiong, G., Yan, K., & Zhou, X. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.03.009 · Cited by 52
“Many literatures have reviewed the opportunities, challenges and solutions of federal learning framework in the field of wireless communication [27–30].”
BackgroundWu, B., Fang, F., & Wang, X. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3317300 · Cited by 53
“This necessitates data-intensive machine learning (ML) to effectively utilize the massive amount of data for supporting intelligent services and applications [1], [2].”
BackgroundWu, 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
“In general, the traditional ML models are trained using a centralized way, which requires a central server to assemble the distributed raw data of users for model training [2].”
MethodDistributed computing in multi-agent systems: a survey of decentralized machine learning approaches
Ahmed, I., Syed, M. A., Maaruf, M., & Khalid, M. (2024) · Computing · doi:10.1007/s00607-024-01356-0 · Cited by 55
Bandit-based data poisoning attack against federated learning for autonomous driving models
Wang, S., Li, Q., Cui, Z., Hou, J., & Huang, C. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120295 · Cited by 41
Convergence 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
“…CIFAR-10, and SST-2) with different 6 The imbalanced independent identically distributed (IID) data distribution is adopted, where a factor c n ∈ [ 1 , 10 ] is randomlygeneratedforalldevices,andtrainingsamples(500for MNIST, 50000 for CIFAR-10, and 67349 for SST-2) are shuffled and partitioned…”
Mehta, M., Bimrose, M. V., McGregor, D. J., King, W. P., & Shao, C. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.04.031 · Cited by 37
Zhang, H., Yang, Z., Tian, Y., Zhang, H., Di, B., & Song, L. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3285592 · Cited by 39
“The update of the CNN models of the l -th vehicle using one sample of training data can be given by [44] w l ← w l − η ∇ Loss ( w l , b ) , (26) where η is the learning rate and b is a sample uniformly selected from the training data v l .”
MethodMachine Learning-Powered Radio Frequency Sensing: A Review
Santra, A., Wang, P. P., Shaker, G. S. A., R., B. S. M., Dolmans, G., Chen, Y., Shariati, N., & Pandharipande, A. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3547673 · Cited by 40
“issues in model convergence and performance [262].”
Communication-Efficient Federated Data Augmentation on Non-IID Data
Wen, H., Wu, Y., Li, J., & Duan, H. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00381 · Cited by 39
“, smart healthcare [17], automated industrial processes [23], and vehicular services [20].”
BackgroundToward Cooperative Federated Learning Over Heterogeneous Edge/Fog Networks
Wang, S., Hosseinalipour, S., Aggarwal, V., Brinton, C. G., Love, D. J., Su, W., & Chiang, M. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.005.2200925 · Cited by 34
“This shows that CFL obtains substantial improvements over both baselines in terms of energy and time savings for the same target ML performance. mobile communication servers (e.g., at sporting events), a natural next step for D2S collaboration involves non-stationary edge/fog servers [14].”
BackgroundDecentralized Federated Learning for Road User Classification in Enhanced V2X Networks
Barbieri, L., Savazzi, S., & Nicoli, M. (2021) · 2021 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops50388.2021.9473581 · Cited by 30
Self-citationSlimFL: Federated Learning With Superposition Coding Over Slimmable Neural Networks
Yun, W. J., Kwak, Y., Baek, H., Jung, S., Ji, M., Bennis, M., Park, J., & Kim, J. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2022.3231864 · Cited by 35
“One is located in [2, 10], and the other is in [5,∞], respectively.”
BackgroundSelf-citationBarbieri, L., Kianoush, S., Nicoli, M., Serio, L., & Savazzi, S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3530265 · Cited by 34
“Accordingly, each device produces a local representation of the global model via consensus-based aggregation strategies over the received local model parameters (or surrogate quantities) obtained from neighboring learners [8], [9].”
Self-citationEnergy-Efficient Massive MIMO for Federated Learning: Transmission Designs and Resource Allocations
Vu, T. T., Ngo, H. Q., Dao, M. N., Ngo, D. T., Larsson, E. G., & Le‐Ngoc, T. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3222749 · Cited by 29
Collusive Model Poisoning Attack in Decentralized Federated Learning
TAN, S., Hao, F., Gu, T., Li, L., & Liu, M. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3342901 · Cited by 29
“Furthermore, DFL has demonstrated great potential in practical applications such as IIoT [6], Internet of Vehicles [7], the unmanned aerial vehicle (UAV) Network [8], and wireless IoT networks [9].”
BackgroundFederated fusion learning with attention mechanism for multi-client medical image analysis
Irfan, M., Malik, K. M., & Muhammad, K. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102364 · Cited by 27
Tan, G., Yuan, H., Hu, H., Zhou, S., & Zhang, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3385913 · Cited by 27
Space–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
“To explore emerging opportunities of FL for the industrial network, open issues have been discussed, focusing on automated vehicles and collaborative robotics [16].”
A Layer Selection Optimizer for Communication-Efficient Decentralized Federated Deep Learning
Barbieri, L., Savazzi, S., & Nicoli, M. (2023) · IEEE Access · doi:10.1109/access.2023.3251571 · Cited by 25
“Most of FL implementations use a Parameter Server (PS) to orchestrate the training process [19] while novel decentralized FL policies [24], [25], [26], [27], [28] exploit direct interactions among the agents.”
MethodSelf-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
“sensitive information and therefore cannot be collected in the practical deployment [3].”
BackgroundIndoor Flying Networks for 6G: Concepts, Challenges, Enabling Technologies, and Opportunities
Ahmad, R., Ayyash, M., Salameh, H. B., El-Khazali, R., & Eigala, H. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.009.2200559 · Cited by 24
Kou, W.-B., Wang, S., Zhu, G., Luo, B., Chen, Y., Ng, D. W. K., & Wu, Y. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342134 · Cited by 32
“To tackle these challenges, currently there are three methods mainly to compress model parameters or gradient size: quantization-based, sparsification-based, and distillation-based strategies [11].”
Method6G V2X Technologies and Orchestrated Sensing for Autonomous DrivingPreprint
Mizmizi, M., Brambilla, M., Tagliaferri, D., Mazzucco, C., Debbah, M. A., Mach, T., Simeone, R., Mandelli, S., Frascolla, V., Lombardi, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.16146 · Cited by 19
“Federated machine learning [15] is emerging as key technology for cooperative CAVs that perform several automated functions relying on bigdata.”
BackgroundSelf-citationFederated Learning for 6G Security: A Survey on Threats, Solutions, and Research Directions
de Alwis, C., Aouedi, O., Xu, J., Wang, S., Siriwardhana, Y., Hewa, T. M., Zeydan, E., Sandeepa, C., & Liyanage, M. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3663434 · Cited by 29
Information-Theoretic Decentralized Secure Aggregation With Passive Collusion Resilience
Zhang, X., Li, Z., Li, S., Wan, K., Ng, D. W. K., & Caire, G. (2026) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2026.3678509 · Cited by 22
“Our results establish the fundamental performance limits of DSA, providing insights for the design”
Byzantine Fault-Tolerance in Federated Local SGD Under $2f$-Redundancy
Gupta, N., Doan, T. T., & Vaidya, N. H. (2023) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2023.3237489 · Cited by 22
“Besides traditional machine-learning applications [2], federated optimization now also finds application in networked systems, e.g., Internet of Vehicles [3] and industrial control systems [4], [5].”
BackgroundDevice Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
Wang, S., Morabito, R., Hosseinalipour, S., Chiang, M., & Brinton, C. G. (2024) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2024.3423673 · Cited by 21
A framework for energy and carbon footprint analysis of distributed and federated edge learning
Savazzi, S., Kianoush, S., Rampa, V., & Bennis, M. (2021) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc50174.2021.9569307 · Cited by 17
“FL (CFL), the participating devices mutually exchange their local ML model parameters, possibly via mesh, or deviceto-device (D2D) communication links [2], and implement distributed weighted averaging [6], [7], [8].”
BackgroundMethodInfluentialSelf-citationChen, W., Chen, S., Leng, J., Wang, J., Guan, Y., Meng, M. Q. ‐., & Zhang, H. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3438165 · Cited by 22
“In certain operational environments, such as those involving high altitude and high-risk climbing tasks, the conflict between robot computation and autonomy is particularly pronounced [35], [36].”
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
“, in an Industrial Internet of Things (IIoT) scenario [8] or for teleoperated driving [9], training data must be shared with low latency to guarantee that collaborative machines are synchronized.”
BackgroundFLaMAS: Federated Learning Based on a SPADE MAS
Rincon, J. A., Julián, V., & Carrascosa, C. (2022) · Applied Sciences · doi:10.3390/app12073701 · Cited by 16
“Recognizing this, the main objective of this study was to demonstrate how multi-agent system (MAS) technology can be exploited to improve necessary data exchange and the aggregation process in a federated learning system [10] by improving its flexibility and dynamism.”
BackgroundZhai, Z., Yuan, X., & Wang, X. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3385443 · Cited by 20
“Moreover, in application scenarios like autonomous robotics and collaborative driving [4], centralized FL may not be realizable due to the absence of an available central PS.”
Overview of fair federated learning for fairness and privacy preservation
Kim, D., Oh, K., Lee, Y., & Woo, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128568 · Cited by 18
Model-based Reinforcement Learning in FedMA Approach for Industry 4.0
Natrayan, L. (2025) · International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) · doi:10.1109/icerect65215.2025.11376321 · Cited by 14
“Notably, Deep RL provides more opportunities for digital twin-based IIoT and efficient data management in IIoT [14].”
Combining federated learning and control: A survey
Weber, J., Gurtner, M., Lobe, A., Trachte, A., & Kugi, A. (2024) · IET Control Theory and Applications · doi:10.1049/cth2.12761 · Cited by 22
A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification
Barbieri, L., Savazzi, S., Kianoush, S., Nicoli, M., & Serio, L. (2023) · IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD) · doi:10.1109/camad59638.2023.10478391 · Cited by 18
“Decentralized CFA techniques [2], [3] do not employ the PS as the devices mutually exchange their local model parameters, i.”
BackgroundMethodSelf-citationTackling Resource Allocation for Decentralized Federated Learning: A GNN-Based Approach
Meng, C., Tang, M., Setayesh, M., & Wong, V. W. S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3562834 · Cited by 13
“In industrial Internet of Things (IIoT), DFL can be trained by harnessing distributed sensor data across industrial facilities [14], [15].”
Symbolic knowledge injection meets intelligent agents: QoS metrics and experiments
Agiollo, A., Rafanelli, A., Magnini, M., Ciatto, G., & Omicini, A. (2023) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-023-09609-6 · Cited by 17
“MACs consider solely multiplications and summations as they represent the most common computations in NNs. Theoe measures are indicative of the amount of memory required either to fit the whole sub-symbolic predictor—total number of parameters—or to run it—FLOPs and MACs.”
Optimized Data Sampling and Energy Consumption in IIoT: A Federated Learning Approach
Hsu, Y.-L., Liu, C., Wei, H., & Bennis, M. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3216353 · Cited by 12
“Compared with CL, the benefits of energy saving in FL paradigms were discussed in [20], [21], [24], and [25], and numerically investigated in [26].”
BackgroundSelf-citationCommunication-efficient Distributed Learning in V2X Networks: Parameter Selection and Quantization
Barbieri, L., Savazzi, S., & Nicoli, M. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001364 · Cited by 13
“Federated Learning (FL) [5], [6], in particular, is a promising candidate for ML model training over interconnected vehicles.”
BackgroundSelf-citationMajeed, A., & Hwang, S. O. (2024) · IEEE Access · doi:10.1109/access.2024.3413069 · Cited by 14
“…have explored FL use in almost all fields, including medical practices [27], [28], dealing with COVID-19 [29], [30], [31], finance [32], robotics [33], the automotive industry [34], mobile robotics [35], autonomous driving [36], [37], traffic prediction [38], and IoT-based applications [39].”
BackgroundWeighted Average Consensus Algorithms in Distributed and Federated Learning
Tedeschini, B. C., Savazzi, S., & Nicoli, M. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3528982 · Cited by 12
“Recently, a distributed version of FL, known as consensus-based FL [50], [51], [52], [53], has been proposed to address some of the challenges associated with PS-based FL, i.e., with centralized approaches [54].”
Self-citationExploring Age-of-Information Weighting in Federated Learning Under Data Heterogeneity
Wang, K., Ding, Z., So, D. K. C., & Ding, Z. J. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3545456 · Cited by 13
“Compared with centralized learning that requires offloading raw data to the server, in federated learning, learning tasks are executed collaboratively without data sharing, and hence, privacy security can be improved [5].”
Qiao, Y., Han, T., Wu, Z., Jin, G., Zhang, Q., & Xu, Q. (2026) · Entropy · doi:10.3390/e28020151 · Cited by 12
“FL, in particular, offers a privacy-preserving approach where models are trained locally on distributed data without the need to centralize sensitive information, which is crucial when dealing with non-i.i.d. data across different sites [68,69].”
Unifying ground and air: a comprehensive review of deep learning-enabled CAVs and UAVs
Zia, M. U., Xiang, W., Huang, T., Ahmad, J., Chattha, J. N., Naqvi, I. H., & Butt, F. A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11425-1 · Cited by 13
Soft Actor Critic Reinforcement Learning for Decentralized Secured Drone System
Lakshmaiya, N., Kaliappan, S., Muthukannan, M., Priyadharshini, R., & Ramya, M. (2025) · IEEE International Conference on ICT in Business Industry & Government (ICTBIG) · doi:10.1109/ictbig68706.2025.11323988 · Cited by 11
“…overloaded with huge amount of data that can be overcome using the Federated systems adopting the techniques like path planning that fix the trajectory based data collection and the volume of data is reduced by the knowledge distillation method where the model aggregation is done efficiently [15].”
Decentralized Over-the-Air Federated Learning by Second-Order Optimization Method
Yang, P., Jiang, Y., Wen, D., Wang, T., Jones, C. N., & Shi, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3327610 · Cited by 14
“In practical terms, with the fast advancement of industrial systems, more and more intelligent and autonomous components (e.g., vehicles, robots) are deployed in a networked structure for smart systems [8], [12], which naturally fits for the architecture of decentralized FL.”
BackgroundHaghighi, A., Cheraghi, M., Pocachard, J., Botta‐Genoulaz, V., Jocelyn, S., & Pourzarei, H. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1605682 · Cited by 12
Borazjani, K., Abdisarabshali, P., Nadimi, F., Khosravan, N., Liwang, M., Wang, X., Hong, Y., & Hosseinalipour, S. (2025) · IEEE Internet of Things Magazine · doi:10.1109/miot.2025.3604330 · Cited by 10
“For a detailed discussion, see [3], [4].”
Federated Learning for Lidar Super Resolution on Automotive Scenes
Γκίλλας, Α., Arvanitis, G., Lalos, A. S., & Μουστάκας, Κ. (2023) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp58604.2023.10167942 · Cited by 10
“FL allows multiple clients to collaboratively learn a deep learning model without having to share their own private datasets, ensuring privacy [14].”
BackgroundS2E-DECI: Secrecy and Energy-Efficient Dual-Aware Device-Edge Co-Inference for AIoT
Han, S., Zhang, W., Xu, X., Wang, B., Sun, M., Tao, X., & Zhang, P. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3477953 · Cited by 10
Auction-guided model diffusion for communication-efficient federated learning on non-IID data
Ahn, S.-Y., Kim, S., Kwon, Y., Youn, J., Park, J., & Cho, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108066 · Cited by 10
Federated learning-based aerial image segmentation for collision-free movement and landing
Chhikara, P., Tekchandani, R., Kumar, N., & Tanwar, S. (2021) · ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond (DroneCom) · doi:10.1145/3477090.3481051 · Cited by 12
“[13, 14].”
Picallo, I., López-Iturri, P., Celaya-Echarri, M., Azpilicueta, L., & Falcone, F. (2022) · Mobile Networks and Applications · doi:10.1007/s11036-022-01993-9 · Cited by 11
Shrestha, A. K., Khan, F. A., Shaikh, M. A., Jaberzadeh, A., & Geng, J. (2023) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon59035.2023.10316006 · Cited by 10
“Additionally, DFL mitigates network bottleneck challenges by evenly distributing communication and workloads across nodes, thereby minimizing the risk of congestion or performance delays across the network [10].”
BackgroundDonevski, I., Nielsen, J. J., & Popovski, P. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.709946 · Cited by 13
Barbieri, L., Simeone, O., & Nicoli, M. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095158 · Cited by 9
“Federated Learning (FL) enables the collaborative training of Machine Learning (ML) models without the direct exchange of data in both star and fully decentralized architectures [1, 2, 3].”
BackgroundSelf-citationPoisoning Attacks on Federated Learning for Autonomous Driving
Garg, S., Jönsson, H., Kalander, G., Nilsson, A., Pirange, B., Valadi, V., & Östman, J. (2024) · Linköping electronic conference proceedings · doi:10.3384/ecp208002 · Cited by 11
Metadata
- Authors
- Savazzi, S., Nicoli, M., Bennis, M., Kianoush, S., & Barbieri, L.
- Affiliations
- National Research Council (IT)
- Politecnico di Milano (IT)
- University of Oulu (FI)
- Venue
- IEEE Communications Magazine
- Published
- 2021-02
- Volume
- 59
- Issue
- 2
- Pages
- 16-21
- ISSN
- 0163-6804 (ISSN-L)
- 1558-1896
- OpenAlex
- W3119593986
- Cited by
- 181
- References
- 18
- Citations by year
- 2026: 12 · 2025: 43 · 2024: 44 · 2023: 38 · 2022: 25 · 2021: 19
- FWCI
- 11.13
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Communications Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Virtual Community of Pathological Anatomy (University of Castilla La Mancha) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- 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 Communication Technologies
- Keywords
- federated learning, cooperative driving, connected and automated vehicles, collaborative robotics, smart manufacturing, ultra-reliable low-latency communication, distributed learning, networked multi-agent systems
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.