Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
Open accessThe DOI matches its Crossref record; 231 of the 231 references it cites were found in a registry or an index.
Abstract
In recent years, Federated Learning (FL) has gained relevance in training collaborative models without sharing sensitive data. Since its birth, Centralized FL (CFL) has been the most common approach in the literature, where a central entity creates a global model. However, a centralized approach leads to increased latency due to bottlenecks, heightened vulnerability to system failures, and trustworthiness concerns affecting the entity responsible for the global model creation. Decentralized Federated Learning (DFL) emerged to address these concerns by promoting decentralized model aggregation and minimizing reliance on centralized architectures. However, despite the work done in DFL, the literature has not (i) studied the main aspects differentiating DFL and CFL; (ii) analyzed DFL frameworks to create and evaluate new solutions; and (iii) reviewed application scenarios using DFL. Thus, this article identifies and analyzes the main fundamentals of DFL in terms of federation architectures, topologies, communication mechanisms, security approaches, and key performance indicators. Additionally, the paper at hand explores existing mechanisms to optimize critical DFL fundamentals. Then, the most relevant features of the current DFL frameworks are reviewed and compared. After that, it analyzes the most used DFL application scenarios, identifying solutions based on the fundamentals and frameworks previously defined. Finally, the evolution of existing DFL solutions is studied to provide a list of trends, lessons learned, and open challenges.
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
“Data breaches within third-party services could lead to the loss of proprietary vehicle models or private data, compromising user privacy and vehicle security on a large scale [7, 12, 22].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In DFL, achieving consensus among participating nodes is crucial to ensure that model updates are coherent and reflect the contributions of all peers [12].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Data security is another critical challenge, as the transmission and storage of sensitive data create vulnerabilities that may lead to breaches, exposing both individual and aggregate information [7, 12, 22].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The choice of topology affects the overall privacy, robustness, flexibility, fault tolerance, and communication costs of the network [12].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [12]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While CFL is effective in various scenarios, it has limitations such as a single point of failure, bottlenecks at the server, and various privacy risks associated with centralized data aggregation [12].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [12]
Experimental — accuracy not yet measured
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“[16] 2022 Privacy and protection of medical data exchanged between healthcare entities Cross-silo Decentralized Real ResNet18 ResNet50 DenseNet121 Custom algorithm Synchronous Sequential ImageNet [166] Private”
BackgroundLearning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 3×
“[22] 2021 Novel method proposed by DFL with P2P communication between autonomous vehicles Cross-device Centralized Decentralized Simulation CNN Custom algorithm Synchronous Schematic MNIST [172] KITTI [219]”
MethodInfluentialCommunication-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 5×
“Furthermore, the controller can select participants based on a preassigned probability calculated according to participation in the federation [4].”
BackgroundInfluentialDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“Specifically, it is a procedure to train a model using a second NN as a reference instead of learning directly from the ground truth of the data [141].”
MethodnuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
Learning Word Vectors for Sentiment Analysis
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011) · Cited by 6,960
The multimodal brain tumor image segmentation benchmark (BRATS)
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2377694 · Cited by 6,781 · cited 3×
“[96] 2022 Detect brain tumor segmentation, using representative clinical datasets Cross-device Centralized Decentralized Real U-Net CFA FedPer Synchronous Asynchronous Random BRATS [167] Private [88] 2022 Detect misconduct model on specific sites from any learning iteration Cross-device Centralized Decentralized Simul…”
MethodInfluentialThe MovieLens Datasets: History and Context
Harper, F. M., & Konstan, J. A. (2016) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2827872 · Cited by 6,627 · cited 2×
“[20] 2020 Proactive caching scheme where vehicles are trained from sparse data, mitigating privacy risks Cross-device Decentralized Real CF-VAE FedAvg Asynchronous Random MovieLens [195]”
MethodFederated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · cited 1×
“Regarding CFL, several works have attracted immense interest from academia and industry [37].”
Background
Research works printed but not linked: 12
- 2022, DISCO—Distributed collaborative machine learning
- Li, 2022, Mining latent relationships among clients: Peer-to-peer federated learning with adaptive neighbor matching, arXiv:2203.12285 · arXiv
- 2022, Tensorflow federated
- Go, 2009, Twitter sentiment classification using distant supervision
- 2016, Geo dataset browser
- Dos, 2021, Predicting human eye diseases
- Savazzi, 2020, Federated learning: mmWave MIMO radar dataset for testing
- 2016, Avito context ad clicks
- 2021, IoT device identification
- Koch, 2021, On digital ethics for artificial intelligence in hybrid military operations
- Reiser, 2022, Creiser/drone-detection
- Fisher, 2019, CVONLINE: Image databases
Cited by
Decentralized 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
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
Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W. (2024) · Healthcare · doi:10.3390/healthcare12242587 · Cited by 228
Distributed Foundation Models for Multi-Modal Learning in 6G Wireless Networks
Du, J., Lin, T., Jiang, C., Yang, Q., Bader, C. F., & Han, Z. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.009.2300501 · Cited by 187
“SL enhances privacy by transmitting only non-sensitive features, reduces bandwidth, and boosts efficiency by allocating lighter tasks to local devices and distributed paradigm, federated learning (FL) is well-suited for assisting the data parallelism [11].”
BackgroundA systematic review of federated learning: Challenges, aggregation methods, and development tools
Guendouzi, S. B., Ouchani, S., Assaad, H. E., & Zaher, M. E. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103714 · Cited by 199
Remote Sensing and Geospatial Analysis in the Big Data Era: A Survey
Dritsas, E., & Τρίγκα, Μ. (2025) · Remote Sensing · doi:10.3390/rs17030550 · Cited by 255
Edge Intelligence for Internet of Vehicles: A Survey
Yan, G., Liu, K., Liu, C., & Zhang, J. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3378509 · Cited by 186
“However, DFL topologies may face challenges such as increased communication overhead and convergence complexity, necessitating careful design of communication protocols, client selection strategies, and trust mechanisms to enable efficient and secure operation [66].”
BackgroundHasan, M. K., Habib, A. K. M. A., Islam, S., Safie, N., Ghazal, T. M., Khan, M. A., Alzahrani, A. I., Alalwan, N., Kadry, S., & Masood, A. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.02.044 · Cited by 97
Fedstellar: A Platform for Decentralized Federated Learning
Beltrán, E. T. M., Gómez, Á. L. P., Feng, C., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122861 · Cited by 103
“Fedstellar, which extends from p2pfl library (Guijas, 2022b), facilitates the training of FL models in a decentralized fashion across many physical and virtualized devices (Martínez Beltrán et al., 2023a).”
BackgroundMethodSelf-citationTariq, A., Serhani, M. A., Sallabi, F., Barka, E. S., Qayyum, T., Khater, H. M., & Shuaib, K. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3438264 · Cited by 154
Medical Imaging Applications of Federated Learning
Sandhu, S. S., Gorji, H. T., Tavakolian, P., Tavakolian, K., & Akhbardeh, A. (2023) · Diagnostics · doi:10.3390/diagnostics13193140 · Cited by 115
“For more information regarding the various types of FL setups concerning the computational burden, as discussed in this section, please refer to the work of Beltran et al. [16].”
Chen, X., Xu, G., Xu, X., Jiang, H., Tian, Z., & Ma, T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3362974 · Cited by 100
“In traditional HFL architectures, the failure of a central coordinator can impede the entire system’s operation [31].”
Privacy-preserving in Blockchain-based Federated Learning systems
Sameera, K. M., Nicolazzo, S., Arazzi, M., Nocera, A., A., R. R. K., Vinod, P., & Conti, M. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.04.024 · Cited by 133
Wang, X., Wang, B., Wu, Y., Ning, Z., Guo, S., & Yu, F. R. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3446585 · Cited by 128
“Authors in [26] provide an in-depth analysis of Decentralized Federated Learning (DFL).”
Qiao, C., Li, M., Liu, Y., & Tian, Z. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3399612 · Cited by 111
“However, there is a privacy issue since it assumes a trusted server or third party orchestrating all agents, which also introduces the communication bottleneck for the server [41].”
Abimannan, S., El-Alfy, E.-S. M., Hussain, S., Chang, Y., Shukla, S., Satheesh, D., & Breslin, J. G. (2023) · Sustainability · doi:10.3390/su151813951 · Cited by 93
FederatedTrust: A solution for trustworthy federated learning
Sánchez, P. M. S., Celdrán, A. H., Xie, N., Bovet, G., Pérez, G. M., & Stiller, B. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.10.013 · Cited by 103
Self-citationFederated learning for green and sustainable 6G IIoT applications
Khanh, Q. V., Nguyen, D. C., Anh, D. V., & Quý, N. M. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101061 · Cited by 73
Toward Federated Large Language Models: Motivations, Methods, and Future Directions
Cheng, Y., Zhang, W., Zhang, Z., Zhang, C., Wang, S., & Mao, S. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3503680 · Cited by 105
TrustBCFL: Mitigating Data Bias in IoT Through Blockchain-Enabled Federated Learning
Zhou, S., Li, K., Chen, Y., Yang, C., Liang, W., & Zomaya, A. Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3379363 · Cited by 74
Federated learning and TinyML on IoT edge devices: Challenges, advances, and future directions
Ramadan, M. N. A., Ali, M. A. H., Khoo, S. Y., & AlKhedher, M. A. (2025) · ICT Express · doi:10.1016/j.icte.2025.06.008 · Cited by 72
Alsharif, 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
Adam, M., & Baroudi, U. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3506214 · Cited by 46
IronForge: An Open, Secure, Fair, Decentralized Federated Learning
Yu, G., Wang, X., Sun, C., Wang, Q., Yu, P., Ni, W., & Liu, R. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3329249 · Cited by 58
YOGA: Adaptive Layer-Wise Model Aggregation for Decentralized Federated Learning
Liu, J., Liu, J., Xu, H., Liao, Y., Wang, Z., & Ma, Q. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3329005 · Cited by 60
“To overcome the problem of PS-based architecture, Decentralized Federated Learning (DFL) [5], which enables the clients to collaborate and learn from each other by exchanging model parameters directly, has been proposed.”
BackgroundFedcs: Efficient communication scheduling in decentralized federated learning
Zong, R., Qin, Y., Wu, F., Tang, Z., & Li, K. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102028 · Cited by 47
Ajala, O. A., Arinze, C. A., Ofodile, O. C., Okoye, C. C., & Daraojimba, O. D. (2024) · World Journal of Advanced Engineering Technology and Sciences · doi:10.30574/wjaets.2024.11.1.0060 · Cited by 62
Riedel, P., Schick, L., von Schwerin, R., Reichert, M., Schaudt, D., & Hafner, A. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02234-z · Cited by 51
Xu, H., Seng, K. P., Ang, L.-M., & Smith, J. (2024) · IEEE Access · doi:10.1109/access.2024.3422211 · Cited by 50
Gelenbe, E., Gül, B. C., & Nakıp, M. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101340 · Cited by 54
Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping
Sun, P., Liu, X., Wang, Z., & Liu, B. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02338 · Cited by 52
“The traditional centralized feder-♯ ated learning (CFL) framework relies on a central server to coordinate the distributed model training process [3].”
BackgroundNetwork for Distributed Intelligence: a Survey and Future Perspectives
Campolo, C., Iera, A., & Molinaro, A. (2023) · IEEE Access · doi:10.1109/access.2023.3280411 · Cited by 44
“Hence, decentralized server-less Federated Learning solutions, also referred to as swarm learning , are gaining momentum [39], [40], [41].”
BackgroundAlsaleh, S., Menaï, M. E. B., & Al-Ahmadi, S. A. (2024) · IEEE Access · doi:10.1109/access.2024.3460468 · Cited by 40
“This is mostly used in applications where the data are sensitive and need to be protected (e.g., healthcare applications) [61].”
BackgroundMethodDas, S. K., Mudi, R., Rahman, M. S., Rabie, K. M., & Li, X. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3466858 · Cited by 27
“7 [77], [78], [79], [80], [81], [82], [83]. that account for asynchronous cooperation and predictive techniques is essential for dynamic wireless networks.”
BackgroundImplementation of Big AI Models for Wireless Networks with Collaborative Edge Computing
Zeng, L., Ye, S., Chen, X., & Yang, Y. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.004.2300479 · Cited by 42
“…centralized federated learning that resorts to a central coordinator (e.g., the cloud) to orchestrate the pipeline and train a global model, decentralized federated learning allows clients to exchange model updates directly with each other [7], as in that in centralized federated learning, where…”
BackgroundUnleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
Li, Y., Wang, H., Xu, W., Xiao, T., Liu, H., Tu, M., Wang, Y., Yang, X., Zhang, R., Yu, S., et al. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3568279 · Cited by 56
Zhen, L., Kamarudin, N. H., Kok, V. J., & Qamar, F. (2025) · IEEE Access · doi:10.1109/access.2025.3589620 · Cited by 44
Real-world federated learning in radiology: hurdles to overcome and benefits to gain
Bujotzek, M., Akünal, Ü., Denner, S., Neher, P., Zenk, M., Frodl, E., Jaiswal, A., Kim, M., Krekiehn, N. R., Nickel, M., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae259 · Cited by 29
Improving Equipment Maintenance—Switching from Corrective to Preventative Maintenance Strategies
West, J., Siddhpura, M., Evangelista, A., & Haddad, A. (2024) · Buildings · doi:10.3390/buildings14113581 · Cited by 34
Landscape of machine learning evolution: privacy-preserving federated learning frameworks and tools
Nguyen, G., Díaz, J. S.-P., Calatrava, A., Berberi, L., Lytvyn, O., Kozlov, V. Y., Tran, V., Moltó, G., & García, Á. L. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-11036-2 · Cited by 39
Survey of Federated Learning Models for Spatial-Temporal Mobility Applications
Belal, Y., Mokhtar, S. B., Haddadi, H., Wang, J., & Mashhadi, A. (2024) · ACM Transactions on Spatial Algorithms and Systems · doi:10.1145/3666089 · Cited by 41
“For a full comparison across the described FL frameworks refer to [61], while peer-to-peer FL frameworks have been extensively compared in [7].”
BackgroundFederated Learning for 6G Networks: Navigating Privacy Benefits and Challenges
Sandeepa, C., Zeydan, E., Samarasinghe, T., & Liyanage, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3513832 · Cited by 41
“The clients are nodes in a Peer-to-Peer (P2P) network, such that collaborative model training is possible [61].”
A Survey on Energy-Efficient Design for Federated Learning over Wireless Networks
Dang, X.-T., Vu, B., Nguyen, Q.-S., Tran, T.-D., Eom, J.-S., & Shin, O. (2024) · Energies · doi:10.3390/en17246485 · Cited by 36
Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning
Mittone, G., Tonci, N., Birke, R., Colonnelli, I., Medić, D., Bartolini, A., Esposito, R., Parisi, E., Beneventi, F., Polato, M., et al. (2023) · ACM International Conference on Computing Frontiers (CF) · doi:10.1145/3587135.3592211 · Cited by 28
“Table 1 compares the FL frameworks found mature by [7].”
BackgroundInfluentialCollusive 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
“…of clients, which has the characteristics of decentralization, strong dynamic network, weak participant connectivity, and no unified global model, thereby providing more convenient conditions for malicious participants to launch poisoning attacks [10], and posing a great threat to system security.”
BackgroundEbrahimi, E., Sober, M., Hoang, A.-T., Ileri, C. U., Sanders, W., & Schulte, S. (2024) · IEEE International Conference on Blockchain (Blockchain) · doi:10.1109/blockchain62396.2024.00017 · Cited by 27
“Furthermore, on-chain model aggregation requires high computational costs [11].”
BackgroundKumar, A., Maulik, A., & Chinmaya, K. A. (2025) · IETE Technical Review · doi:10.1080/02564602.2025.2522083 · Cited by 33
“…is highly scalable, allowing the integration of numerous participants across geographically distributed systems; and it enhances system resilience by reducing reliance on centralized infrastructure and mitigating the risks associated with single points of failure or communication bottlenecks [187].”
Toward Decentralized Intelligence: A Systematic Literature Review of Blockchain-Enabled AI Systems
Jasem, M. S. A., Clark, T. D., & Shrestha, A. K. (2025) · Information · doi:10.3390/info16090765 · Cited by 40
DART: A Solution for decentralized federated learning model robustness analysis
Feng, C., Celdrán, A. H., von der Assen, J., Beltrán, E. T. M., Bovet, G., & Stiller, B. (2024) · Array · doi:10.1016/j.array.2024.100360 · Cited by 31
Self-citationCommunication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
Mohammadabadi, S. M. S., Yang, L., Yan, F., & Zhang, J. (2024) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs60910.2024.00069 · Cited by 40
“A centralized server, both prone to latency bottlenecks [7], [8] and susceptible to failures and targeted attacks [9], can significantly undermine the reliability of the entire distributed learning process.”
BackgroundATD Learning: A secure, smart, and decentralised learning method for big data environments
Alzubaidi, L., Jebur, S. A., Jaber, T. A., Mohammed, M. A., Alwzwazy, H. A., Saihood, A., Gammulle, H., Santamaría, J., Duan, Y., Fookes, C., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102953 · Cited by 28
FLADEN: Federated Learning for Anomaly DEtection in IoT Networks
Hendaoui, F. A., Meddeb, R., Trabelsi, L., Ferchichi, A., & Ahmed, R. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104446 · Cited by 25
Asheralieva, A., Niyato, D. T., & Wei, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3543295 · Cited by 24
“This can lead to ENs’ dropouts and failures, which hinder the DFL training [9], [10], [15].”
InfluentialTanim, S. A., Aurnob, A. R., Mridha, M. F., Safran, M., Alfarhood, S., & Che, D. (2024) · IEEE Access · doi:10.1109/access.2024.3454690 · Cited by 24
AccDFL: Accelerated Decentralized Federated Learning for Healthcare IoT Networks
Wei, M., Yu, W., & Chen, D. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3486122 · Cited by 30
“These paradigms aim to improve the efficiency and privacy of healthcare data management to handle the two primary challenges, i.e., privacy protection and optimization of federation communications [2], [3], [4].”
Jiang, L., Ming, X., & Zhang, X. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3559978 · Cited by 26
“Beltr (cid:1) an et al. reviewed the application of DFL in hospitals, noting that DFL models demonstrated promising results comparable to traditional centralized models [25].”
Yang, H., Liu, H., Yuan, X., Wu, K. M., Ni, W., Zhang, J. A., & Liu, R. P. (2025) · Applied Sciences · doi:10.3390/app15126587 · Cited by 31
ALDP-FL for adaptive local differential privacy in federated learning
Cui, L., & Wu, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-12575-6 · Cited by 36
“Federated learning is a privacy-preserving distributed collaborative learning framework 46 , primarily aimed at achieving joint model training across multiple participants without sharing raw data, as shown in Fig.”
A Vertical Federated Multiview Fuzzy Clustering Method for Incomplete Data
Li, Y., Hu, X., Yu, S., Ding, W., Witold Pedrycz, C., Yeo, C. K., & Liu, Z. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3526978 · Cited by 18
“Federatedlearning(FL)[21],[22]isregardedasacollaborative learningframeworkthatcanrealizecross-clientanalyticswith privacypreservation.”
DFedADMM: Dual Constraint Controlled Model Inconsistency for Decentralize Federated Learning
Li, Q., Shen, L., Li, G., Yin, Q., & Tao, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3546659 · Cited by 28
Mitigating communications threats in decentralized federated learning through moving target defense
Beltrán, E. T. M., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2024) · Wireless Networks · doi:10.1007/s11276-024-03667-8 · Cited by 21
“DFL enhances decentralization by facilitating model aggregation at multiple nodes, drastically reducing dependence on a single central server and enabling direct, pairwise model sharing among the network nodes.”
BackgroundSelf-citationFedCD: A Hybrid Federated Learning Framework for Efficient Training With IoT Devices
Liu, J., Huo, Y., Qu, P., Sun, X., Liu, Z., Ma, Q., & Huang, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3368216 · Cited by 26
Toward Collaborative and Cross-Environment UAV Classification: Federated Semantic Regularization
Fu, X. G., Wang, Y., Lin, Y., Ohtsuki, T. O., Adebisi, B., Gui, G., & Sari, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3531773 · Cited by 19
“Integrating the samples from multiple surveillance systems through wireless transmission could address this challenge, but it is infeasible or impractical due to limited communication resources, data privacy concerns, or country regulations [8].”
Bernal, S. L., Pérez, M. Q., Beltrán, E. T. M., Pérez, G. M., & Celdrán, A. H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129537 · Cited by 25
Self-citationMeta-XPFL: An Explainable and Personalized Federated Meta-Learning Framework for Privacy-Aware IoMT
Serhani, M. A., Tariq, A., Qayyum, T., Taleb, I., Din, I., & Trabelsi, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3541844 · Cited by 23
“This approach reduces communication overhead and enables more efficient aggregation of model updates [20].”
Zhao, H., Xia, T., Xia, Y., Yang, J., Liu, M., & Zhu, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3557906 · Cited by 17
“However, traditional FL relies on central servers, which become bottlenecks as clients grow, leading to higher latency and limited scalability [12], [13].”
Scalability and performance evaluation of federated learning frameworks: a comparative analysis
Soudan, B., Abbas, S., Kubba, A. A., Waraga, O. A., Talib, M. W. A., & Nasir, Q. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02453-4 · Cited by 26
Laidi, R., Merabtine, N., Djenouri, D., Latif, S., Qadir, H. A., Djenouri, Y., & Balasingham, I. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3557475 · Cited by 21
“Smart contracts can automate the aggregation process, streamlining collaboration without needing a central coordinator [48], [49], [50].”
Algorithmic Techniques for GPU Scheduling: A Comprehensive Survey
Chab, R., Setia, S. K., & Li, F. (2025) · Algorithms · doi:10.3390/a18070385 · Cited by 25
Energy Efficiency in Network Slicing: Survey and Taxonomy
Donatti, A. W., Machado, M. C., MARTINEZ, M. A. L., Antunes, S. S. R., SOUZA, E. C. F., Corrêa, S. L., Ferreto, T. C., Monteiro, J. A. S., Martins, J. S. B., & CARVALHO, T. C. (2025) · IEEE Access · doi:10.1109/access.2025.3590365 · Cited by 15
“Some of the current general trends in terms of ML-based slicing include : Embedded ML agents in the SP architecture [26]; Distributed learning methods such as FL to provide architectural slicing capabilities [27]; and Architectural data-driven approaches that support machine learning methods [20].”
Trustworthy decentralized collaborative learning for edge intelligence: A survey
Yu, D., Xie, Z., Yuan, Y., Chen, S., Qiao, J., Wang, Y., Yu, Y. H., Zou, Y., & Zhang, X. L. (2023) · High-Confidence Computing · doi:10.1016/j.hcc.2023.100150 · Cited by 20
Shaheen, M., Farooq, M. S., & Umer, T. (2023) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan13010001 · Cited by 15
Cyber Deception: Taxonomy, State of the Art, Frameworks, Trends, and Open Challenges
Lopez, P. B., Pérez, M. G., & Nespoli, P. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3594788 · Cited by 68
“In this sense, federated architectures enable collaborative learning without centralizing data, increasing privacy and security [204].”
Self-citationA Survey of Federated Learning for mmWave Massive MIMO
Nugroho, V. A., & Lee, B. M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3397302 · Cited by 20
“3) FL Network Architecture: Based on the network architecture of the FL model, FL could be classified in centralized FL (CFL), decentralized FL (DFL), and semi DFL (SDFL) [48] as depicted in Fig.”
MethodLiu, Y., Yin, J., Zhang, W., An, C., Xia, Y., & Zhang, H. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3523350 · Cited by 21
“FL is viewed as a practical approach to fueling Transformer by resolving the issue of inadequate data quality in the public domain by utilizing high-quality data stored in private domains [22].”
Decentralized Federated Learning for Private Smart Healthcare: A Survey
Cheng, H., Qu, Y., Liu, W., Gao, L., & Zhu, T. (2025) · Mathematics · doi:10.3390/math13081296 · Cited by 21
Multimodal large language models for medical image diagnosis: Challenges and opportunities
Zhang, A., Zhao, E., Wang, R., Zhang, X., Wang, J., & Chen, E. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104895 · Cited by 21
Securing Federated Learning With Blockchain in the Medical Field: Systematic Literature Review
Wang, X., Xie, Y., Chen, X., Yang, J., Li, R., Gao, W., Yan, Z., Zhou, H., & Ye, Z. (2026) · Journal of Medical Internet Research · doi:10.2196/79052 · Cited by 28
“Insufficient mining resources slow down block generation and verification, hindering the efficient execution of large-scale tasks [123].”
Nemane, S. G., Sarad, V. M., Tulaskar, D. P., Marode, T. P., Bhangdiya, V. K., Agrawal, L., Avthankar, A., Kondylakis, H., Kulkarni, M. B., Bhaiyya, M. L., et al. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10629-0 · Cited by 16
Xiong, J., Ye, Y., Wang, Q., Dong, X., Lu, T., & Ma, D. (2024) · Electric Power Systems Research · doi:10.1016/j.epsr.2024.111007 · Cited by 17
Enabling efficient and low-effort decentralized federated learning with the EdgeFL framework
Zhang, H., Bosch, J., & Olsson, H. H. (2024) · Information and Software Technology · doi:10.1016/j.infsof.2024.107600 · Cited by 22
Federated learning in food research
Fendor, Z., van der Velden, B. H. M., Wang, X., Carnoli, A. J., Mutlu, O., & Hürriyetoğlu, A. (2025) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2025.102238 · Cited by 37
“For instance, decentralized FL may be more prone to cybersecurity problems (Martínez Beltrán et al., 2023).”
Hu, Y., Li, Q., Chai, Y., Wu, D., Lu, L., Shi, N., Teng, Y., & Zhang, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3384546 · Cited by 22
“Federated learning (FL) has been widely investigated and regarded as a distributed computing paradigm in which multiple distributed nodes undergo individual training before sharing parameters [26].”
BackgroundDang, X.-T., & Shin, O. (2024) · Electronics · doi:10.3390/electronics13101827 · Cited by 14
“They contribute to the modernization of human life across diverse applications such as smart cities, smart healthcare, and autonomous cars [2,3].”
BackgroundFragkou, E., & Katsaros, D. (2024) · Future Internet · doi:10.3390/fi16110413 · Cited by 21
“In this case, we have three categories: horizontal , vertical and transfer federated learning [18].”
Li, J., Khalatbarisoltani, A., Che, Y., Yang, Y., & Hu, X. (2025) · Energy storage materials · doi:10.1016/j.ensm.2025.104681 · Cited by 11
Liang, Z.-Y., Liu, G., Yi, R., Yang, M. Y., Jiang, R., Luo, Y., & Ma, Y.-S. (2025) · Information · doi:10.3390/info16121066 · Cited by 16
“The core concept of federated learning is to train models on decentralized data [54], leveraging multi-party collaboration to train a global model without centrally sharing raw data.”
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 23
“Instead, some form of decentralized model aggregation occurs over a peer-to-peer network, aiming to address the downsides of centralized FL mentioned above.”
An asynchronous federated learning-assisted data sharing method for medical blockchain
Gan, C., Xiao, X., Zhang, Y., Zhu, Q., Bi, J., Jain, D. K., & Saini, A. (2024) · Applied Intelligence · doi:10.1007/s10489-024-06172-9 · Cited by 15
Beltrán, E. T. M., Sánchez, P. M. S., Bovet, G., Stiller, B., Pérez, G. M., & Celdrán, A. H. (2025) · IEEE Communications Magazine · doi:10.1109/mcom.003.2400401 · Cited by 13
“DFL [3] improves the previous limitations each participant to train local models and contribute to the global model through decentralized aggregation.”
Self-citationHe, Z., Zhu, G., Zhang, S., Luo, E., & Zhao, Y. (2025) · Electronics · doi:10.3390/electronics14112183 · Cited by 20
Zhu, W., Shi, L. X., Wei, K., Zhou, Y., Wang, Z., Xiong, Z., & Li, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3588537 · Cited by 17
Li, X., Li, H., Sun, C., Fan, Q., Han, Z., & Leung, V. C. M. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3587225 · Cited by 21
“This efficient use of edge hardware resources not only improves model performance, but also reduces the burden on central cloud servers and overall resource overhead.”
DeSA: Decentralized Secure Aggregation for Federated Learning in Zero-Trust D2D Networks
Wang, L., Lu, Z., Li, M., Wang, J., Gai, K., & Chen, X. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3658996 · Cited by 11
Ge, H., Pokhrel, S. R., Liu, Z., Wang, J., & Li, G. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110758 · Cited by 18
Federated Learning: Challenges, SoTA, Performance Improvements and Application Domains
Schoinas, Ι., Triantafyllou, A., Ioannidis, D., Tzovaras, D. K., Drosou, A., Votis, K., Λάγκας, Θ., Argyriou, V., & Sarigiannidis, P. G. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3458088 · Cited by 14
Kim, H., Dorjgochoo, S., Park, H., & Lee, S.-J. (2025) · Electronics · doi:10.3390/electronics14091790 · Cited by 16
Asheralieva, A., & Niyato, D. T. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3565005 · Cited by 12
“To deal with these drawbacks, other works (e.g., [5], [7], [18], [19], [20], [21], [22], [23], and [24]) consider applying decentralized federated learning (DFL) [16], [17] to UAV networks.”
InfluentialGraph Neural Networks for the Optimization of Collaborative Federated Learning Energy Efficiency
Yang, N., Wang, S., Liu, Y., Brinton, C. G., Yin, C., & Chen, M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3582911 · Cited by 12
MID-LLM: Enhancing Medical Image Diagnostics With LLMs in a Blockchain AI Framework
Kumar, R., Rao, Y., Kumar, J., Mawuli, C. B., Ali, W., & Zeng, S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3583408 · Cited by 13
“The server aggregates these updates using the FedAverage algorithm [7], [28] where w i represents the local model parameters, D i is the local dataset of client i , and (cid:4) j ( w i ) is the loss for sample j .”
Metadata
- Authors
- 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.
- Affiliations
- Department of Information and Communications Engineering, University of Murcia, Murcia, Spain
- Universidad de Murcia (ES)
- Bundesamt für Rüstung armasuisse (CH)
- University of Zurich (CH)
- ORCID
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2023
- Volume
- 25
- Issue
- 4
- Pages
- 2983-3013
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W4386766438
- Cited by
- 625
- References
- 220
- Citations by year
- 2026: 175 · 2025: 282 · 2024: 145 · 2023: 23
- FWCI
- 58.92
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Union (PID2021-122466OB-I00, TED2021-129300B-I00)
- the Swiss Federal Office for Defense Procurement (CyberForce, DEFENDIS)
- Universit?t Z?rich
- Fundaci?n S?neca (21629/FPI/21)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- decentralized federated learning, communication mechanisms, performance indicators, federated learning frameworks, application scenarios, open problems
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.