Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
Open accessThe DOI matches its Crossref record; 230 of the 230 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 6,961
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…”
MethodInfluentialFederated 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].”
BackgroundFashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108 · cited 2×
“[222] 2023 Blockchain-enhanced DFL for efficient and privacy-protective data sharing Cross-device Decentralized Simulation CNN FedAvg Asynchronous Scheduling FMNIST [190]”
Method
Research works printed but not linked: 13
- 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
- 10.1145/3340531.3411866 · DOI
- 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 401–500 of 626
V2X-Based Decentralized Singular Value Decomposition in Dynamic Vehicular Environment
Zhao, J., Lin, M.-B., & Vinel, A. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91813-1_9 · Cited by 1
Federated learning for distributed intrusion detection in IoT networks
Du, Q., Li, B., Shao, Z., Wu, Y., & Yang, C. G. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-329032-9.00009-9 · Cited by 2
Romero, V., Matsui, T., Matsuda, Y., Suwa, H., & Yasumoto, K. (2025) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops65533.2025.00062 · Cited by 1
“Unlike conventional decentralized federated learning [11], which addresses the absence of an orchestrator by enabling successive rounds of communication to agree on a common model state [12], [13], opportunistic settings face challenges from parameter overlap and dynamic node mobility, complicating…”
Seaswarm: Mitigating Stragglers in Cross-Silo Swarm Learning via Semi-asynchronous Communication
Yang, X., Hu, C., & Cheng, D. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9961-2_34 · Cited by 1
Wireless Resource Efficient Distributed Learning with Deep Joint Source-Channel Coding
Matsumura, I., & Suto, K. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11100602 · Cited by 1
Sahoo, S. K., Dash, A., Mishra, S. K., & Humayun, M. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-80949-1_3 · Cited by 3
Hierarchical Bidirectional Aggregation for Federated Learning Under Concept Drift
Hemadasa, N., Kaaser, D., & Schulte, S. (2025) · International Conference on Fog and Mobile Edge Computing (FMEC) · doi:10.1109/fmec65595.2025.11119244 · Cited by 1
“While traditional FL assumes a star topology, where a central server directly communicates with all clients [14, 27, 36], real-world applications often employ more complex topologies.”
Survey of Privacy Threats and Countermeasures in Federated Learning
Hayashitani, M., Mori, J., & Teranishi, I. (2025) · International Conference on Federated Learning Technologies and Applications (FLTA) · doi:10.1109/flta67013.2025.11336767 · Cited by 3
“In contrast, decentralized HFL eliminates the central server, allowing clients to communicate directly, thereby reducing communication costs [5].”
Human-Centric Enterprise Security: Advancing Access Control through AI-Driven AdministrationPreprint
Mariam, A., Berrada, A., & Nakamura, S. (2024) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/6utz2 · Cited by 4
Assessing the Sustainability and Trustworthiness of Federated Learning ModelsPreprint
Celdrán, A. H., Feng, C., Sánchez, P. M. S., Zumtaugwalda, G. ́. B. A. B. S. L., Bovet, G., & Stiller, B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4829587 · Cited by 2
Self-citationWaqas, M., Abbas, S., Farooq, U., Khan, M. A., Alharbi, M., & Asiff, M. (2024) · Research Square · doi:10.21203/rs.3.rs-4412965/v1 · Cited by 1
Innocenti, L., Antonelli, M., Ourselin, S., & Lorenzi, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-323761-4.00034-1 · Cited by 2
Paul, T., & Kumar, S. (2025) · doi:10.36227/techrxiv.174585953.31012414/v1 · Cited by 1
Editorial: Fourth Quarter 2023 IEEE Communications Surveys and Tutorials
Niyato, D. T. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3330559
Exploring Federated Learning for Data Integration: A Structured Literature Review
Awick, J.-P., Schumann, G., & Gómez, J. M. (2023) · International Conference on Big Data, Knowledge and Control Systems Engineering (BdKCSE) · doi:10.1109/bdkcse59280.2023.10339771 · Cited by 2
Addressing Limitations of TinyML Approaches for AI-Enabled Ambient Intelligence: Position Paper
Bonneau, A., Mouël, F. L., & Mieyeville, F. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-74640-6_16 · Cited by 3
Minimizing Noise in Location Privacy Protection Through Equipment Error Consideration
Isawa, R., Sei, Y., Tahara, Y., & Ohsuga, A. (2024) · International journal of electrical and computer engineering systems · doi:10.32985/ijeces.15.3.7
Dong, W., & Feng, S. (2024) · Stat · doi:10.1002/sta4.669
“For more details refer to Yuan et al. (2016), Ye et al. (2022) and Martínez Beltrán et al. (2023).”
BackgroundHosseinalipour, S. (2024) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v3i1.31216
(POSTER) Network Testbed for Experimenting With Decentralized Federated Learning
Mandal, A., Thareja, K., & Ruth, P. (2024) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot61029.2024.00119
“The latter is called Decentralized Federated Learning (DFL) [3], [4].”
BackgroundMulti-stage Pricing Mechanism in Duopoly Computation Markets
Chen, P., Wang, Q., Liu, J., Wang, Y., & Guo, Z. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-5760-2_2
Piaseczny, A., Ruzomberka, E., Parasnis, R., & Brinton, C. G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3462674 · Cited by 2
“6) Effects of Changing Attack Characteristics: Graph properties such as connectivity, size, or the dynamics of node and edge changes constitute a large part of the properties that influence the analyzed model.”
FedTrojan: Corrupting Federated Learning via Zero-Knowledge Federated Trojan Attacks
Chang, S., Liu, Y., Lin, Z., Zhu, H., Zhu, B., & Wang, C. (2024) · International Workshop on Quality of Service · doi:10.1109/iwqos61813.2024.10682906 · Cited by 3
“The key feature of federated learning (FL) [1] [2] is that de-centralized participants use their private data to independently train their local models, and server estimates the global model according to the local models uploaded by the participants.”
MethodVehicular Traffic Flow Prediction via Decentralized Federated Meta-Learning
Selvia, A., Singh, A., & Wu, W. (2024) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice62917.2024.00016
“Decentralized FL (DFL) distinguishes itself by eliminating centralization altogether [12].”
BackgroundLawal, K. N., Mata, M. O., Olaniyi, T. K., & Gibson, R. M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-73122-8_28
Tigchelaar, K., Ziabari, S. S. M., & Mulder, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0026-7_16
Federated Learning in Mesh Networks
Wang, X., Chen, Y., & Dobre, O. A. (2024) · Wiley eBooks · doi:10.1002/9781394227952.ch6 · Cited by 2
Integrating Federated Learning for Edge Intelligence in Cybersecurity and Cloud Computing
Avanija, J., Ramrao, N., Madhavi, K. R., Goundar, S., Balaji, V., & Hasini, A. A. (2024) · Advances in information security, privacy, and ethics book series · doi:10.4018/979-8-3693-6859-6.ch005
Liu, W., Li, K., Zheng, Y., She, W., & Tian, Z. (2025) · Computing · doi:10.1007/s00607-024-01405-8
Zhang, R., & Deng, X. (2024) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus61736.2024.10840160
Cheng, H., Liu, W., Qu, Y., Fu, K., & Wang, Q. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00015
Combining Centralized and Decentralized Federated Learning: An Integrated Framework
Yang, J., Kong, Y., Su, H., Guo, Z., Li, Z., & Qian, R. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865286
“Based on the way federated models are constructed, FL can be divided into two groups: centralized, known as Central-ized Federated Learning (CFL), and decentralized, known as Decentralized Federated Learning (DFL) [5].”
Reflecting on how to Analyze Poisoning Attacks in Gossip Learning
Pham, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-80946-0_32
Fuzzy Logic-based Enhanced Edge Server Selection for Hierarchical Federated Learning
Du, Z., Wu, C., Lin, Y., Zhong, L., Djahel, S., & Chong, P. H. J. (2024) · Globecom · doi:10.1109/globecom52923.2024.10900992
“The decentralization of computing tasks addresses bandwidth limitations and network congestion challenges, significantly improving distributed learning systems’ overall performance [8].”
On Decentralized Learning with Stochastic Subspace Descent
Sharma, S. D., Sharma, P., & Rajawat, K. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889456
“Variants of Stochastic Gradient Descent (SGD) [4], such as distributed SGD [5], [6] and federated learning [7], are widely used in many decentralized settings.”
PPDL: Efficient Dropout-Resilient Aggregation for Privacy-Preserving Decentralized Learning
Ghavamipour, A. R., Zhao, B. Z. H., & Türkmen, F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-3531-3_5
FEDGA: FL with Dynamic Gradient and Group Normalization
Ma, C., Yang, X., & Xu, G. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4506-0_17
Enhancing Data Privacy and Security in Corporate Environments via Federated Learning: A Case Study
Hijji, M. (2025) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit63348.2025.10989287 · Cited by 1
“Federated learning (FL) is an emerging approach that decentralises the machine learning process, which has emerged in response to these challenges [6].”
Hamad, M., Kühr, M., Mouratidis, H., Kalogeraki, E.-M., Gizelis, C. A., Papanikas, D., Bountioukos-Spinaris, A., Skandylas, C., Raptis, E., Alexopoulos, A., et al. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10992768
“Moving forward, the project will explore swarm learning to enhance decentralization and peer-to-peer model sharing [19].”
GLow – Flower Ingurunean Oinarritutako Esamesa bidezko Ikasketa Estrategia Simulatua
Belenguer, A., Pascual, J. A., & Navaridas, J. (2025) · IkerGazte Nazioarteko ikerketa euskaraz · doi:10.26876/ikergazte.vi.03.08
“Era berean, Mart´ınez Beltr´an et al. (2023)-ek existitzen diren IFD inguruneei buruzko informazioa biltzen duten ekar-penen falta aldarrikatzen dute, hala nola, pertsonalizazio mailaren arabera sailkapen bat proposatu.”
Federated Learning Setting for E-Learning Course Recommendations
Jolović, M., Kostić, D., Joksimović, A., Tahirović, T., & Lukovac, P. (2025) · International Scientific Conference Sinteza · doi:10.15308/sinteza-2025-35-40
“Centralized FL functions between a server node and several client nodes, as described in Figure 1 [11].”
FedDPG: An Adaptive Yet Efficient Prompt-Tuning Approach in Federated Learning Settings
Shakeri, A., Zhang, W. E., Beheshti, A., Chen, W., Yang, J. Y., & Yang, L. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8186-0_4
“Federated learning systems can be broadly categorized into centralized (CFL) and decentralized (DFL) frameworks [1].”
Decentralized Sparse Matrix Multiplication Under Byzantine Attacks
Ghasvarianjahromi, S., Yakimenka, Y., & Kliewer, J. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3581053
“One notable example is in IoT networks, where multiple devices possessing partial sensor data must collaboratively process information without relying on a central server [11], [12].”
Embracing Diversity: Enhancing Generalization in Heterogeneous Federated Learning
Duan, W., Zhang, S., & Tang, H. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030411
“To mitigate catastrophic forgetting, Memory ReplayGANs [11] replay pseudo-samples to reduce forgetting of old knowledge; DFL [12] addresses latency and vulnerabilities caused by centralized bottlenecks; GradMA [13] proposes a federated learning method inspired by continual learning to correct…”
Schema Matching Using Federated Learning on a Hybrid Feature Set
Shepelev, A. E., & Stupnikov, S. A. (2025) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661825700142
Wrona, A., Gentile, S., & Santis, E. D. (2025) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit63408.2025.11037088
“To overcome this problem, fully decentralized methods for federated learning have recently been studied in the literature, for example by [19], [20], [21].”
Highly Scaled Federated Learning Simulations for Text Classification
Rudolph, S., Schumann, G., Steffens, L., Karl, M., & Gómez, J. M. (2025) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs65393.2025.11069933
“An alternative to CFL is the "Decentralized Federated Learning" architecture (DFL), in which the aggregation of the local model parameters can be performed by neighboring clients without the need for a central server [3].”
A Utilization Method of Big Data in Blockchain Based on Swarm Learning
Cao, Y., Kang, H., Li, Y., & Zhang, Z. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-93825-2_10
FedCFM: Tackling Client Dropout in Federated Learning through Model Contrastive Fusion
Ren, X., Wang, X., Xu, S., Zhu, L., & Hu, H. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11063751
“(3) Clients randomly have dropout behaviors but the quantity of clients taking part in each round remains fixed [14]: Let P ∈ [0, 1] be the proportion of active clients.”
Fenics: A Modular Framework for Security Evaluation in Decentralized Federated Learning
Saha, S., Nova, S. N., Duvignau, R., & Chiasserini, C. F. (2025) · ACM International Conference on Distributed and Event-Based Systems (DEBS) · doi:10.1145/3701717.3730550
Privacy-preserving federated learning models for healthcare data
Aeron, S. T. (2023) · International Journal of Computing and Artificial Intelligence · doi:10.33545/27076571.2023.v4.i2a.182
Robust clustering federated learning with trusted anchor clients
Zhang, M., Li, Y., Wei, F., Wang, B., & Zhang, Y. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104210 · Cited by 1
Hieu, V. T. T., Quyen, N. H., Hoang, H. D., Duy, P. T., & Pham, V.-H. (2025) · Cluster Computing · doi:10.1007/s10586-025-05247-7 · Cited by 2
“These limitations have driven the development and adoption of decentralized FL (DFL) [18], an advanced approach that aims to minimize dependence on the central aggregation server and enhance the security and scalability of the learning system.”
Behera, L., & Poosapati, V. (2024) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset2512544
Decentralized Federated Large Model Tuning over Edge Networks with Zeroth-Order Optimization
Chen, Z., Park, J., He, B., Yuan, Y., & Yang, H. H. (2025) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc65529.2025.11148609
“Consequently, leveraging peer-to-peer collaborations among UEs would be a pragmatic paradigm for scalable FL systems [10], [11].”
ForkRL: Deep Reinforcement Learning-Based Forking Prevention in Blockchain-Enabled Federated IoMT
Ajay, S. K., Sharma, R., & Kumar, S. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3612438
“The iterative process continues until global model convergence is achieved [9].”
Coded Distributed Computing Over Multi-Server Clustered Network for Federated Learning
Mou, W., Gu, S., Zhang, Z., Lei, G., Zhang, Q., & Xiang, W. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-spring65109.2025.11174461
Deshpande, P. M., Sharma, R., Sinha, S., & Kulkarni, D. V. (2025) · New Review of Information Networking · doi:10.1080/13614576.2025.2554577
Wu, S. (2025) · International Conference on Big Data, Artificial Intelligence and Digital Economy · doi:10.1145/3767052.3767073
“…new data are based on the first 3 and last 3 digits of the original data, respectively, according to the sub-stitution rules of permutation matrix 𝑃 , map 𝑓 to data, which means performing the inverse operation on 𝑓 to complete the permutation of financial risk data bytes in the database [6].”
FederNet: A Network and Device-Aware Emulation Platform for Federated Learning BenchmarkingPreprint
Boiano, A., Avanzini, M., Brambilla, M., Nicoli, M., & Redondi, A. E. C. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5615841
Information Entropy-Based Scheduling for Communication-Efficient Decentralized Learning
Nagar, J., Chen, Z., Kountouris, M., & Stavrou, P. A. (2025) · Machine learning for signal processing ... · doi:10.1109/mlsp62443.2025.11204341
“Collaborative training of a machine learning (ML) model with decentralized data and model aggregation offers benefits over centralized learning, such as lower communication costs, enhanced privacy, increased scalability, and greater robustness against a single point of failure [1], [2].”
Improving Communication-Efficiency for Decentralized Federated Clustering
Nardi, M., & Valerio, L. (2025) · Machine learning for signal processing ... · doi:10.1109/mlsp62443.2025.11204233
Privacy-Preserving Decentralized Federated Learning for Heterogeneous Graphs
Ma, L., Xu, R., Liu, L., Sun, S., Li, C., & Wang, L. (2025) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc67675.2025.00110
“Furthermore, in light of concerns regarding untrusted servers [9], researchers have recently begun exploring decentralized FL (DFL) frameworks [10] that do not rely on a central server.”
FLAg-SwaP: Distributed Federated Learning Aggregation using Particle Swarm-based Placement
Ali-Pour, A., Bekrani, S., Samizadeh, L., & Gascon‐Samson, J. (2025) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) · doi:10.1109/acsos66086.2025.00018 · Cited by 1
“A commonplace communication model for SDFL would be the Client/Server model, similar to CFL [9].”
BeDFL: A Blockchain-Enabled Decentralized Federated Learning in a Non-trusted Environment
Nguyen, X. T., Le, D. H. N., Minh, Q. T., & Phan, T. N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09321-9_11
Sequential Model Averaging-Based Decentralized Learning for Low Overhead and Fast Convergence
Zhao, J., Yang, C., & Liu, T. (2025) · IEEE Communications Letters · doi:10.1109/lcomm.2025.3630324
“With decentralized learning, multiple nodes collaboratively train a deep neural network (DNN) [1].”
Afifi, G., & Mokhtar, B. M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5733105
Topological Optimization and Routing for Reliable Communication Networks: A New Heuristic Method
Chen, J., Sun, J., Chen, J., Li, S., Fang, C., Wang, Z., Pan, C., Zhang, Y., & Zhang, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5006-4_7
Paul, T., & Kumar, G. S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5743198
S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning
Sánchez, P. M. S., Beltrán, E. T. M., Feng, C., Bovet, G., Pérez, G. M., & Celdrán, A. H. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227231 · Cited by 2
“Decentralized Federated Learning (DFL) addresses these limitations by adopting a peer-to-peer approach, eliminating the need for a central server [8].”
Self-citationRoyal FLush: A MAS-Based Platform for Decentralized Federated Learning Based on SPADE Agents
Enguix, F., Rincon, J. A., Celdrán, A. H., & Carrascosa, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-07638-0_7
Self-citationOnline Decentralized Federated Multi-task Learning With Trustworthiness in Cyber-Physical Systems
Odeyomi, O. T., Olaosebikan, S., Ajibuwa, O., & Ige, O. (2025) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw63273.2025.00102
“Recent architecture favors a fully decentralized setting where clients communicate directly without the need to route through a central server [5], [6].”
Distributed Fine-Tuning of Vision Transformer Models
Qureshi, M. I., & Khan, U. A. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226387
“Under the assumption of bi-directional communication, some decentralized federated learning methods are proposed [10], [11].”
Singh, P., Sharma, A., & Aggarwal, M. (2025) · doi:10.1109/cises66934.2025.11265631
Faroongsarng, C., & Nupairoj, N. (2025) · doi:10.1109/incit66780.2025.11276076
On Asynchronous Multiparty Session Types for Federated Learning
Prokić, I., Prokić, S., Ghilezan, S., Scalas, A., & Yoshida, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-11176-0_11
The metaverse shift: adapting to decentralized computing in federated learning for healthcare
Yogi, M. K., & Atti, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-33789-5.00022-4
SDFL: A privacy-preserving byzantine-robust decentralized federated learning scheme
Quan, H.-Y., Qian, Y.-Y., Tian, H., Liu, X., Li, Y., Wang, J., & Zhong, J. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0208
Touat, O., Brunon, J., Belal, Y., Nicolas, J., Sabater, C., Maouche, M., & Mokhtar, S. B. (2025) · International Middleware Conference · doi:10.1145/3721462.3770770 · Cited by 5
AdaptiveShield: Dynamic Defense Against Decentralized Federated Learning Poisoning Attacks
Feng, Y., Zheng, B., Li, T., Wu, C., Ma, Z., Shen, Y., & Ma, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3641896
“In this setup, server roles are dynamically assigned among participating nodes through random selection [40].”
Peng, H., Wu, C., & Xiao, Y. (2025) · Electronics · doi:10.3390/electronics15010074
Decentralized Federated Anomaly Detection in Mobile Networks
Parris, S., Maio, A. D., & Braun, T. I. (2025) · IFIP Wireless Days · doi:10.1109/wd67713.2025.11302745
“DFL has emerged as an effective distributed machine learning approach, enabling collaborative training and model aggregation across decentralized nodes without a central server [7].”
Opportunistic Federated Learning via Digital Signage for Smart Tourism Environments
Sakai, Y., Suwa, H., & Yasumoto, K. (2025) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3714394.3756178
PCIAFL: Personalized and Class Imbalance-Aware Federated Learning for Driver Behavior Classification
OSHO, O., Garg, S., Chakraborty, S., & Das, S. K. (2025) · International Conference on Distributed Computing and Networking (ICDCN) · doi:10.1145/3772290.3772312
Zero-knowledge clustering and selective federated distillation for decentralized federated learning
Chen, S., Pan, S., & Li, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114584
Dynamic-PBFT: Enhanced Consensus in Decentralized Federated Averaging for V2V Networks
Xia, Z., Zhao, J., & Vinel, A. V. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11310770
“However, most current work on DFL still focuses on stable environments where the decentralized nodes can form a stable topology [13].”
FederNet: A network and device-aware emulation platform for federated learning benchmarking
Boiano, A., Avanzini, M., Brambilla, M., Nicoli, M., & Redondi, A. E. C. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.111995 · Cited by 2
Federated learning-based IoMT networks for improved performance of smart health
Öksüz, C., & Sağbaş, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-36556-0.00010-8 · Cited by 2
Yan, W., Li, Q., & Gonsalves, T. (2025) · doi:10.1109/cbdcom68404.2025.00023
“To address these issues, Decentralized Federated Learning (DFL) has gained significant views in both advanced research communities and engineering fields [6].”
Retrieval-Augmented Generation-Based Adaptive State Enhancement for Federated Split Learning
Dong, B., Yan, X., & Zeng, K. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00181
“Despite FL’s advances in privacy preservation, it continues to face issues such as uneven resource allocation, high communication overhead, and suboptimal training efficiency [5].”
Chandra, N. S., Milovanova, M. M., Vasilyeva, O. N., Polineni, T. N. S., Nishant, N., & Verma, A. K. (2025) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat66372.2025.11368399
“This survey classifies federated learning based on data partitioning, privacy, models, communication, and system diversity [2].”
Qiu, H. (2025) · International Conference on Cyber Security and Information Engineering (ICCSIE) · doi:10.1109/iccsie65832.2025.00070
“FL enables collaborative model training while keeping data localized, achieving secure cooperation through the principle of “data stays put, models move” [5,6].”
Rajagopal, S., Shieh, C., Siva Shankar, S., Maithili, K., & Chakrabarti, P. D. P. (2026) · Soft Computing · doi:10.1007/s00500-025-11025-9 · Cited by 1
Duan, M., ZHANG, X., Fan, L., Liu, Y., Jiang, J., & Zhang, H. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3662666
“Edge devices are constantly generating a substantial volume of private data, including photos and voice, which are valuable for developing deep neural networks [1], [2], [3], [4].”
Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
Chongder, S. (2026) · Cureus Journal of Computer Science. · doi:10.7759/s44389-026-00028-0 · Cited by 1
Federated learning, privacy and accuracy
Marwala, T. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-36322-1.00029-8
Edge AI for Ultra-Fast Personalized Recommendation Systems in E-Commerce
Sundar, D. S., Tyagi, L. K., Kannimuthu, S., Amirtharaj, D., Ugli, S. S. D., & Karthikayen, A. (2025) · International Conference on Innovations and Emerging Technologies in AI & Communication Systems (IETACS) · doi:10.1109/ietacs68750.2025.11385447
“Decentralized machine learning is known as federated learning, where data is processed on the user’s devices [12].”
Trust-free Personalized Decentralized Learning
Li, Y., Li, Y., Du, J., Shao, Y., Liang, M., & Ye, G. (2026) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp68355.2026.00073 · Cited by 3
“Conversely, fully Decentralized (DFed) approaches [5] typically rely on local gossip protocols.”
Beyond Parameters: Locally-Guided Knowledge Distillation for Decentralized Federated Learning
Soltani, B., Zhou, Y., Thabet, S. K. S., Alhazmi, E., Yao, L., & Sheng, Q. Z. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00080
“DFL eliminates the need of a central server by enabling direct peer-to-peer communication among clients [6]–[10].”
Nair, S. R., & Nair, P. P. (2025) · International Conference on Smart and Intelligent Systems (SISCON) · doi:10.1109/siscon66686.2025.11409167
“Such limitations could be overcome by Federated Learning [4]–[7], which has developed as a decentralized way to develop secure and privacy-preserving machine learning models.”
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.