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
Items 501–600 of 626
Backdoor-Aware Adaptive Aggregation for Wireless Ad Hoc Federated Learning
Muramatsu, A., & Ochiai, H. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00083
“For example, DFL attracts attention in Industry 4.0 to enable communication between devices and sensors without a central server [10].”
InfluentialBlockchain based semi-Decentralized personalized federated learning
Liu, Y., Lu, Y., Zhu, G., Liu, S., Li, R., Yang, K., & Wang, J. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112197 · Cited by 1
ColNet: Collaborative Optimization in Decentralized Federated Multi-Task Learning Systems
Feng, C., Kohler, N. F., Wang, Z., Niu, W., Celdrán, A. H., Bovet, G., & Stiller, B. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401930 · Cited by 3
Self-citationFRISC: Mitigating Privacy Leakage in Federated Learning through Frequency‐domain Feature Screening
Wu, S., Baker, T., Wang, Y., Tan, Y., Li, Y., & Ren, M. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70640 · Cited by 1
Opportunistic Model Ensembling for Decentralized Learning over Intermittent Edge Networks
Alegarbes, B. J., Romero, V., Matsui, T., Matsuda, Y., Suwa, H., & Yasumoto, K. (2025) · IEEE Annual Congress on Artificial Intelligence of Things (AIoT) · doi:10.1109/aiot66900.2025.00023
“This scenario diverges from traditional decentralized federated learning, which typically relies on regular, orchestrated communication rounds to converge on a shared global model [13].”
Gao, Q., Han, W., Fan, J., Di, Y., Bao, J., Zhang, R., & Gao, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114992
Privacy Preservation Techniques with Federated Learning in IoT Context
Serban, C. M., Sebestyen, G., & Hângan, A. (2025) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp68926.2025.11427183
Hao, P., Le, T. D., Berezkin, A., & Kirichek, R. (2025) · International Conference on Information, Control, and Communication Technologies (ICCT) · doi:10.1109/icct67028.2025.11427421
“The optimization landscape for federated learning [10] encompasses a diverse range of approaches addressing various aspects of system performance, including communication efficiency, convergence acceleration, and resource allocation.”
Asynchronous Decentralized Federated Learning Deconstructs Excessively Large Batches
Wang, Z., Wang, F., Gursoy, M. C., & Velipasalar, S. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432271
“…practice since no central server is required [5], but also provides additional benefits such as improved scalability in scenarios with a large number of users [6], increased robustness against single-node-failures [7], and adaptability to diverse communication protocols and network topologies [8].”
Mitigating Poisoning Attack Coalitions in FL: A Non-Linear Personalized Approach
Besrour, S., Couturier, A., & Almhana, J. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432196
Secure and Efficient AAV-Assisted Maritime Surveillance via QoS-Aware Edge Computing
Andreou, A., Mavromoustakis, C. X., Markakis, E., Bourdena, A., & Mastorakis, G. (2025) · Globecom · doi:10.1109/globecom59602.2025.11431638
Quinello, R., & Costa, B. K. (2026) · International Journal of Construction Management · doi:10.1080/15623599.2026.2636734 · Cited by 1
Mamidala, V., Yalla, R. K. M. K., Devarajan, M. V., Yallamelli, A. R. G., Ganesan, T., & Bouchair, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8187-9.ch011
Design and implementation of DFL framework based on EdgeX platform in digital twin network
Tuan, N. A., Moe, S. J. S., Khan, A. N., & Kim, D. H. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108496 · Cited by 1
Privacy-Preserving Federated Learning for DDoS Detection in Distributed Systems
Ambareen, K., Harsha Jain, H. J., Mohith, D., S, H. K. C., & Umrao, S. (2025) · International Conference on Advancement in Futuristic Technologies (ICAFT) · doi:10.1109/icaft66710.2025.11452998
“1 illustrates the general FL concept [2], and Fig.”
InfluentialGómez, Á. L. P., Beltrán, E. T. M., Sánchez, P. M. S., & Celdrán, A. H. (2026) · IEEE Access · doi:10.1109/access.2026.3681545 · Cited by 6
Self-citationCommunication-efficient decentralized learning for intelligent networked systems
Jeong, E. (2024) · theses.fr (ABES) · doi:10.70675/bf617b44z43eaz4310zb1bdz5f5779d80456
Chang, R.-I., Lu, W.-X., & Yang, C. (2026) · Electronics · doi:10.3390/electronics15081658
Federated Learning and Optimization for Lung Cancer Detection Using FedRes-Net Model
Wei, X. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s021800142657017x
DFLADMM-M: Decentralized Federated Learning via Momentum-Accelerated ADMM
Xiao, S., Yu, J., Wang, G., Liu, W., Hu, Q., & Cao, B. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477188
“Owing to these advantages, DFL has been increasingly adopted in a wide range of applications, including edge intelligence, IoT, and privacy-preserving machine learning [7].”
Decentralized Federated Learning With Period Gradient Tracking Over Time-Varying Networks
Shi, F., Chen, Y., Huang, Q., Huang, T., Liu, G., & Shen, L. (2026) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2026.3685244
“To address this concern, Decentralized Federated Learning (DFL) [8], [9], [10] is introduced to eliminate the central server, directing each client to communicate solely with its neighboring clients.”
Decentralized Federated Learning With Energy Harvesting Devices
Zhang, K., Cao, X., & Letaief, K. B. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3683553 · Cited by 3
“Consequently, decentralized federated learning (DFL) has gained attention as an appealing alternative [15], [16].”
Basics, constraints, and future potential of machine learning in human–machine interaction
Gupta, K., Gupta, S., & Bajaj, V. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44638-2.00014-2
Beltrán, E. T. M., Giryes, P., Bovet, G., Stiller, B., Pérez, G. M., & Celdrán, A. H. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108528
Self-citationRahaman, S. U., Shaik, M., Patchipulusu, S., Kapoor, S., & Abdul, M. J. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44638-2.00012-9
Truong, D. M., Pham, B. H., Ta, D. T., Phan, T. N., & Nguyen, T. A. T. (2026) · International Journal of Information Security · doi:10.1007/s10207-026-01257-7
Yang, Y., Zhu, F., Gao, Y., & Wang, L. (2026) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2026.3688250
“However, the conventional paradigm of direct data collection and centralized training poses significant challenges [7].”
Salihovic, A., Abdisarabshali, P., Langberg, M., & Hosseinalipour, S. (2026) · npj Wireless Technology · doi:10.1038/s44459-025-00022-x · Cited by 1
Babu, D. S., Babu, T. S., Garladinne, R., Reddy, T. S., & RAJESHWAR, J. (2025) · De Gruyter eBooks · doi:10.1515/9783112221082-044
Privacy-protected distributed personalized motion under the federated learning model
Xin, C., & Han, Y. Y. (2026) · Discover Internet of Things · doi:10.1007/s43926-026-00353-3
“Because FL can protect data privacy and support decentralized computing, it has been widely used in privacy-sensitive and distributed data processing scenarios [7, 8].”
Federated Learning: A Comprehensive Review of Methods, Challenges, Applications and Trends
BashariRad, B., Choenni, S., & Omar, M. S. B. A. A. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1015368
Asheralieva, A., & Wei, X. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3693874
“…of each node n ’s discriminator/generator are unbiased , i.e., for all θ d/g n , we have [26], [27], [28], [29]: ) Assumption 3: Variances of the stochastic gradients of each node n ’s discriminator/generator are bounded as [26], [27], [28], [29]: for all θ d/g n , where σ, ξ ≥ 0 are constants.”
InfluentialReinforcement Learning for Dynamic Neural Architecture Search in Federated EVCS Security
Hussain, A., Yadav, A., & Ravikumar, G. (2026) · IEEE Texas Power and Energy Conference (TPEC) · doi:10.1109/tpec67884.2026.11513203
“Federated Learning (FL), which allows collaborative model training without disclosing privatized operational data, has become a viable paradigm for EVCS security [4], [5].”
Moe, S. J. S., Khan, Q. W., Nguyen, A. T., Bibi, M., & Kim, D. H. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.05.006
A Privacy-Preserving Step-Size Collection Against Poisoning Attacks for Federated Learning in IoT
Song, J., Wang, J., Guan, X., & Hu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-20080-8_2
Kaur, S., Angurala, M., & Dhillon, P. K. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526100
BSFL: Secure and Efficient Blockchain-Based Split Federated Learning for Internet of Vehicles
Jiang, Z., Chi, C., Liu, Y., Du, H., Jia, Z., Tairan, D., Wu, Q., Guan, Z., Li, D. S., & Susilo, W. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3695964 · Cited by 1
“FL [10], [11], [12] allows multiple parties to collaboratively train a machine learning model without sharing their raw data.”
Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning
Tang, H., Zhu, J., & Tang, X. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11653790
Liu, S., Shen, H., Law, K. L. E., & Chan-Tong, L. A. M. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00911-3
DOCAttack: Data-Oriented Community Attack in Decentralized Federated Learning
Wang, X., Chen, Y., Ye, Q., Son, J., & Dobre, O. A. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3702609 · Cited by 1
Zhengye, L., Jinyu, D., Yuge, B., & Jianheng, T. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115726
A Distributed Multiagent Wireless Federated Learning Algorithm With Local Differential Privacy
Wang, J., & Drager, S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3703324
“Works such as [9] and [11] employ gossip or diffusion averaging for model parameter or gradient aggregation in server-less topologies.”
Privacy-enhanced DDoS detection with federated learning and differential privacy
Mateus, J., Bagula, A., Zodi, G.-A. L., Ajayi, O., & Kahenga, F. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-344433-3.00013-7
Optimization techniques for federated learning algorithms
Kahenga, F., Bagula, A., Das, S. K., Mateus, J., & Ajayi, O. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-344433-3.00009-5
KF4FL: Kalman Filtering for Privacy-Preserving Federated Learning With Momentum
Ren, X., Han, Q., Yang, S., & Yang, Y. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3695289 · Cited by 1
“As an effective alternative, decentralized FL enables distributed learning without a central server, where all servers connect in a peer-to-peer network to directly exchange and aggregate models [36], [37].”
Centralized versus decentralized federated learning
Arévalo, I., & Salmeron, J. L. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-344433-3.00008-3
Eswaramoorthy, V., Mubaraali, L., SathishKumar, S., & Fatima, H. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01403-y
“Effective utilization of the real time data help in not only in fault identification but also in the early prediction of the faults thus allowing for earlier interventions to be employed before getting into a worse state [ 7 , 8].”
InfluentialPrivacy-preserving federated analytics for digital marketing using adaptive weighted aggregation
Haripriya, R., Khare, N., Pandey, M., Bhatia, G. K., Nandurkar, R., Hada, M., Biswas, S., Choudhary, J., Singh, D. P., & Gupta, S. (2026) · Cluster Computing · doi:10.1007/s10586-026-06206-6
“This makes Federated Learning not only a technological advancement but also a strategic enabler for sustainable and trustworthy marketing analytics [15].”
Zouaghia, Z., Kodia, Z., & Saïd, L. B. (2026) · Cluster Computing · doi:10.1007/s10586-026-06164-z · Cited by 1
Son, N. D. H., Ngan, V. D. T., Nha, L. M., Luong, T. D., Pham, V.-H., & Duy, P. T. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111349 · Cited by 1
Ejigu, G. F., Kim, K. T., Qiao, Y., & Hong, C. S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116413
FedLoss: In-Region Location Verification in 6G Networks via Personalized Federated Learning
Piana, M., Rini, S., & Tomasin, S. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11653930
“Addressing non-IID data heterogeneity remains an active area of research, and several approaches have been proposed, including surveys on heterogeneous federated optimization [6].”
Zhang, Y., Li, Z., & Huo, W. (2026) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect68671.2026.11565452
“The smaller the privacy budget ϵ , the stronger the privacy protection, but it may affect the training accuracy of the model [11-12].”
A comprehensive survey on communication optimization and privacy preservation in federated learning
Kunjumon, A., Sarath, G., & Nair, J. J. (2026) · Discover Computing · doi:10.1007/s10791-026-10272-0 · Cited by 3
Quyen, N. H., Pham, V.-H., & Duy, P. T. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133417 · Cited by 1
When Blockchain and Federated Learning Hit it Off: Forging a Novel Proof of Useful Work
Lu, H., Fan, K., Guo, Z., Zhang, K., & Li, H. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3707157
Meng, S., Xiong, Z., Yao, S., Luo, L., & Dai, Y. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113020
Dib, O. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104577 · Cited by 2
BioMutFed+: Mutation-Driven Federated Learning for IIoT
Tallat, R., Wang, X., Hawbani, A., Xu, X., Miao, F., Zhao, L., & Wang, J. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3707971 · Cited by 1
“Understandardassumptionsofsmoothness,boundedgradient variance, and controlled heterogeneity (detailed in Supplementary Section SIV-A), B IO M UT F ED + converges to a stationary point at the rate where [5 , 12] across tasks, gradientvarianceplateauingbyround10,and1.”
AdaComm: Adaptive Committee Sizing for Resilient and Efficient Decentralized Federated Learning
Lan, H., Sun, Y., Huang, T., & Lei, H. (2026) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis70043.2026.11572295
Resource-Aware Decentralized Learning with Rate-Adaptive Quantization
Qiao, J., Liu, Y., Yuan, Y., Zou, Y., Zhang, X., & Yu, D. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571464
“This paradigm inherently mitigates single-point-of-failure risks and adapts dynamically to changes in network connectivity [3], [4], making it ideal for some applications such as healthcare [5], [6], multi-agent coordination [7], [8] and vehicular networks [9], [10].”
A privacy-aware federated learning framework for collaborative healthcare IoT security
Saidi, R., Moulahi, T., Zidi, S., & Mahfoudhi, S. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100944 · Cited by 3
Towards Federated Learning at the Far Edge: From Static Topologies to Generalized Network Graphs
Suimon, T., Rojas, E., Koizumi, Y., Díaz-Fuentes, J., Carrascal, D., & Takemasa, J. (2026) · IFIP Networking Conference (IFIP Networking) · doi:10.23919/ifipnetworking70592.2026.11579054
HITLAP: Human in the Loop AI-Privacy Architecture for Next Generation Banking Automation
Koganti, H., Refonaa, J., Ignatius, A. G., Rao, A. V. S. S. R., Praba, R. S., & Keerthana, N. V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8217-3.ch006
Son, N. D. H., An, N. T. D., Phi, T. T., Thu, N. T., Hoang, H. D., Trong, N. T., Pham, V.-H., & Duy, P. T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9284-5_4 · Cited by 1
Poisson subsampling for large-scale functional data analysis
Yan, X., & He, S. (2026) · Computational Statistics · doi:10.1007/s00180-026-01776-w
FedNP: Novelty preference driven momentum correction for federated long-tailed learning
Yang, C., Xia, H., Song, S., Wu, L., & Peng, J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115927
Game Theory Based Resource Allocation for Energy Efficient Decentralized Federated Learning Systems
Zhou, H., Liu, S., Chen, X., & Zarakovitis, C. C. (2025) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps68340.2025.11590934
Zero Trust Federated Learning with GAN-Augmented Anomaly Detection for Financial Fraud
Shees, A., & Zubair, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.224
A Secure and Resilient Framework for Wildfire Management via UAVs and Blockchain Federated Learning
Lamani, L., Leka, E., Rexha, G., & Aliti, A. (2026) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro70003.2026.11591814
A secure aggregation scheme for DFL based on chain-based cryptographic verification
Wang, B., Lyu, L., Xiaoya, Y., Wang, C., & Zhang, L. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08699-9
Trust-Based Incentive Mechanisms in Semi-decentralized Federated Learning Systems
Shrestha, A. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-22088-2_16 · Cited by 2
“One of the central issues in FL is the vulnerability to malicious or faulty nodes [7, 8].”
Information-Theoretic Secure Aggregation in Decentralized Networks
Zhang, X., Li, Z., Li, S., Wan, K., Ng, D. W. K., & Caire, G. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587614 · Cited by 2
Li, Z., Zhang, X., Zhao, Y., Chen, H., Fan, J., & Caire, G. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587742
Liao, Y.-S., Chang, C.-F., Chiu, T.-C., & Chen, Y.-C. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587871
Sakho, T. M., & Ben‐Othman, J. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587873
“In VANETs, adversaries may exploit eavesdropping, impersonation, Sybil attacks, poisoning, back-door insertion, or denial-of-service attacks to disrupt learning, manipulate shared parameters, or infer sensitive information [2]–[4].”
Event-Triggered Decentralized Distillation over Multiagent Networks
Matsukawa, S., Hayashi, N., & Inuiguchi, M. (2026) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med70602.2026.11598447
“Federated learning (FL) addresses this privacy requirement by letting devices compute updates on their own data and share the information needed for learning [1], [2].”
Decentralized Machine Learning in Healthcare: Federated Learning for IoMT and Beyond
MUGIGAYI, F., Karacan, H., Alli, A. A., Ali, A. B., & Mwondi, L. A. (2026) · International Symposium on AI-Driven Engineering Systems (ISADES) · doi:10.1109/isades69945.2026.11608204
“The development of hybrid FL approaches which combine elements of both centralized and decentralized learning may provide a flexible framework which can address different clinical scenarios [26].”
Pakkir, K. K. R., Kalam, K. K. R., Bontha, S., Pashya, T. R., Balpunuri, S. T. R., & Vepala, T. R. (2026) · International Conference on Computer Networks, Big Data and IoT (ICCBI) · doi:10.1109/iccbi68589.2026.11619696
“Federated Learning (FL) has become a powerful model of decentralized learning that allows local devices to learn with their own data, but only share model parameters with a central aggregation server [10].”
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
Truong, V. V., Nguyen, K., & Kim, T. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108743
“Recent surveys [29, 6] systematically categorize DFL advances, with research focusing on enhancing communication efficiency, convergence speed under non-IID conditions, and robustness to security and privacy threats [30, 31].”
FedMO: Mobility-Aware Client Selection in Federated Learning for Drone Delivery Systems
Jiang, Y., liu, X., xu, J., Yao, A., Jiang, F., & Li, X. (2026) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid68966.2026.00042
Wang, X., Chang, S., Dai, M., Yu, H., Tu, Y., Zhu, H., & Li, B. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00089
“Decentralized federated learning (DFL) [4] mitigates these issues by allowing clients to collaborate through peer-to-peer (P2P) communication, improving scalability and robustness.”
Mobility-Assisted Decentralized Federated Learning: Convergence Analysis and a Data-Driven Approach
Jahani, R., Reza, M. F., & Dai, H. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3720485
“In many settings, persistent connection to a central server for FL is unavailable or undesirable and reliance on a central server can introduce potential single point of failure [2].”
pDFL: Knowledge-aware adaptive aggregation for personalized decentralized federated learning
Wang, S., Tian, Y., Xiang, A., Xiong, J., & Ma, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116749
Decentralized Federated Learning by Partial Message Exchange
Sha, S., Zhou, S., Wang, X., Kong, L., & Li, G. Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3722165 · Cited by 1
“It is widely regarded as a fundamental framework for peer-to-peer, large-scale collaborative learning and has been systematically reviewed in several recent surveys [1], [2].”
Federated Learning for Hybrid Recommendation Systems
Cruz, J., Gaspar, J., Pereira, T., Gonçalves, D., Martinho, D., Marreiros, G., & Santos, J. (2026) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu71813.2026.11637096
“1) Centralized and Decentralized FL: FL is commonly deployed in two architectures [11], [12]: In practice, CFL is still dominant, while DFL is increasingly relevant in settings that prioritize resilience and decentralization [12].”
Wang, S., Tian, Y., Xiong, J., Xiang, A., Bi, R., & Ma, J. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-4812-9
“Consequently, when the server is absent or cannot be trusted, watermark generation, commitment, and verification cannot be securely coordinated among mutually distrustful clients, rendering these methods ineffective in fully decentralized environments [4].”
Di, Y., Shi, H., Jiang, B., Peng, Y., Zhao, H., Zhou, S., Du, S., Liu, Y., Ma, R., & Zhang, W. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3716307
Key-Efficient Decentralized Secure Aggregation with General Security and Collusion Models
Li, Z., Zhang, X., & Caire, G. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11653845
“We have k ∈ [6] \{ u } X k + W u + Z u = k ∈ [6] \{ u } X k = k ∈ [ K ] W k , which ensures that each user can recover the desired sum.”
InfluentialMahi, M. J. N., Naha, R., & Barros, A. (2026) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge72783.2026.00020
“Although prior FL studies focus on single-model architectures [1], [2], [8], limited work explores hybrid TCN-BiLSTM with causal interpretability, sparse feature selection, and resilience under disturbances [17]–[22].”
Alkhodair, A. J. (2026) · Future Internet · doi:10.3390/fi18090455 · Cited by 1
Tuama, A. Y., Hasan, T. M., & Shakir, A. C. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104608
Bandwidth-Aware Decentralized Federated Learning in Wired Networks
Tajiri, K., & Kawahara, R. (2026) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn69946.2026.11662732
“Decentralized federated learning (DFL) addresses the bottleneck problem by removing the master server: each worker directly exchanges models with a subset of other workers [6], [7].”
Liu, D., Zhang, J., Shen, H., & Cao, Y. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134156
Intelligent agents: architectures, learning paradigms, deployment models, and applications
Dritsas, E., & Τρίγκα, Μ. (2026) · Evolutionary Intelligence · doi:10.1007/s12065-026-01259-3 · Cited by 2
Distributed machine learning in precision agriculture: methods, applications, and challenges
Krisnawijaya, N. N. K., Tekinerdoğan, B., & Catal, C. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.102527
Anomaly Based Intrusion Detection System for UAVs Network
Adnan, M., Ali, M., Razi, M. S., & Raja, W. A. E. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-22426-2_49
Vejendla, K. K., Chang, K. (., Aly, S., & Maeng, B. (2026) · Cybersecurity Pedagogy and Practice Journal · doi:10.62273/gpys1669
Ahmadi, K., & Javidan, R. (2026) · Wireless Networks · doi:10.1007/s11276-026-04207-2
Decentralized Vertical Federated Learning via Graph-Based Learning Consensus
Banik, S., Samikwa, E., & Braun, T. I. (2026) · Conference on Local Computer Networks · doi:10.1109/lcn67947.2026.11660802
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.