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 201–300 of 626
BR-FEEL: A backdoor resilient approach for federated edge learning with fragment-sharing
Qi, S., Ma, H., Zou, Y., Yuan, Y., Li, P., & Yu, D. (2024) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2024.103258 · Cited by 4
Federated Learning for Detecting Cyber Attacks in EVCS Using a Lightweight Neural Network
Hussain, A., Yadav, A., & Ravikumar, G. (2025) · IEEE Texas Power and Energy Conference (TPEC) · doi:10.1109/tpec63981.2025.10907147 · Cited by 4
“Furthermore, FL supports scalable implementations across many EVCS units, enabling real-time cyber-attack detection while maintaining data integrity and security [4].”
Towards Federated Multi-Armed Bandit Learning for Content Dissemination Using Swarm of UAVs
Bhuyan, A. K., Dutta, H., & Biswas, S. K. (2025) · ACM Transactions on Internet of Things · doi:10.1145/3733841 · Cited by 4
“Another algorithmic advancement is presented in [24], where UAV trajectory control mechanisms determine whether to continue serving users along a trajectory or to return to the charging station based on real-time conditions.”
InfluentialMitigating malicious model fusion in federated learning via confidence-aware defense
Li, Q., Papageorgiou, P., Liu, G., Gao, M., You, L., Wang, C., & Abdelmoniem, A. M. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103529 · Cited by 11
Qasim, M., Imran, M., Akram, F., Bilal, M. A., & Khan, M. J. (2025) · IEEE Access · doi:10.1109/access.2025.3605380 · Cited by 5
“FL has been increasingly explored in mobile network settings to address privacy concerns and data decentralization [28].”
Demo: A Practical Testbed for Decentralized Federated Learning on Physical Edge Devices
Feng, C., Huber, N., Celdrán, A. H., Bovet, G., & Stiller, B. (2025) · Conference on Local Computer Networks · doi:10.1109/lcn65610.2025.11146362 · Cited by 4
Self-citationPoster: Road to Tiny Reality: Digital Twins for Decentralized AI on Microcontrollers
Asadi, N., Bengu, H. İ., Wulfert, L., Wöhrle, H., & Kellerer, W. (2025) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3680207.3765668 · Cited by 4
Khemaissia, R., Derdour, M., & Djeddai, A. (2024) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais62114.2024.10541291 · Cited by 4
“The communication between trainer and aggregator are reached across proxy [14].”
BackgroundDesigning Robust 6G Networks with Bimodal Distribution for Decentralized Federated Learning
Wang, X., Chen, Y., & Dobre, O. A. (2024) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps61880.2024.10620706 · Cited by 5
Towards Efficient Decentralized Federated Learning: A Survey
Thabet, S. K. S., Soltani, B., Zhou, Y., Sheng, Q. Z., & Wen, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0814-0_14 · Cited by 4
Unlocking potential of open source model training in decentralized federated learning environment
Pavlova, E., Melnikov, G., Yanovich, Y., & Frolov, A. (2025) · Blockchain Research and Applications · doi:10.1016/j.bcra.2024.100264 · Cited by 5
Serverless federated learning: Decentralized spectrum sensing in heterogeneous networks
Çatak, F. Ö., Kuzlu, M., Dalveren, Y., & Özdemir, G. (2025) · Physical Communication · doi:10.1016/j.phycom.2025.102634 · Cited by 4
Unified Analysis of Decentralized Gradient Descent: A Contraction Mapping Framework
Larsson, E. G., & Michelusi, N. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3557332 · Cited by 17
Asymmetrically Decentralized Federated Learning
Li, Q., Zhang, M., Yin, N., Yin, Q., Shen, L., & Cao, X. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3569185 · Cited by 12
“For more related work on DFL, please refer to the survey papers (Gabrielli et al., 2023; Yuan et al., 2023; Beltrán et al., 2022).”
Zhang, X., & Luo, Y. (2025) · Future Internet · doi:10.3390/fi17060243 · Cited by 4
Xu, Y., Zhao, B., Zhou, H., & Su, J. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.053462 · Cited by 8
Sumitra, Sharma, J., & Shenoy, M. V. (2024) · IEEE Access · doi:10.1109/access.2024.3454074 · Cited by 8
Towards Practical Overlay Networks for Decentralized Federated Learning
Hua, Y., Pang, J., Zhang, X., Liu, Y., Shi, X., Wang, B., Liu, Y., & Qian, C. (2024) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp61940.2024.10858583 · Cited by 4
“In most cases, the data on different clients are not identically and independently distributed (non-iid) [11], [33], [4], hence the trained local ML models are substantially different from each other.”
InfluentialIntroducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
Alekszejenkó, L., Antal, P., & Dobrowiecki, T. (2025) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2025.3589612 · Cited by 5
“In such scenarios, server-less, decentralized FL may be helpful [36].”
Khan, Z. A., Xia, Y., Jiang, W., & Anwar, M. S. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3599558 · Cited by 7
“FL, while offering a solution for decentralized training, introduces its own set of challenges, such as non-IID data distributions across different sources, which can affect model performance [6].”
MMDFL: Multi-Model-based Decentralized Federated Learning for Resource-Constrained AIoT Systems
Yan, D., Yang, Y., Hu, M., Fu, X., & Chen, M. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133116 · Cited by 7
Teleportation Links: Mitigating Catastrophic Forgetting in Decentralized Federated Learning
Wang, X., Chen, Y., Ye, Q. J., & Dobre, O. A. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3611109 · Cited by 3
“Through peer-to-peer collaboration, DFL bypasses the need for a central orchestrator, thereby enhancing both scalability and resilience [24], [25].”
Park, J., Kim, S., Lee, J., & Niyato, D. T. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3617965 · Cited by 3
“D ECENTRALIZED federated learning (DFL) is a collaborative training process among mobile devices (MDs), where model parameter aggregation is distributed across neighboring participants [1].”
Li, K., Liang, Y., Lió, P., Ni, W., Dressler, F., Crowcroft, J., & Akan, Ö. B. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3636440 · Cited by 5
Decentralized Federated Learning With Distributed Aggregation Weight Optimization
Zhai, Z., Yuan, X., Wang, X., & Li, G. Y. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3640709 · Cited by 6
“Index Terms —Decentralized federated learning, distributed aggregation weight optimization, communication networks.”
Distributed Deep Learning in IoT Sensor Network for the Diagnosis of Plant Diseases
Papanikolaou, A., Tziouvaras, A., Floros, G., Xenakis, A., & Bonsignorio, F. (2025) · Sensors · doi:10.3390/s25247646 · Cited by 6
“As a result, Federated Learning (FL) has emerged as an effective distributed learning paradigm that enables multiple devices to collaboratively train a global model without sharing their local data, preserving data ownership and privacy [10].”
Hoz, J. L. M. D. L., Islam, M. D. S., Bappy, M. M., & Hayes, M. P. (2026) · Applied Water Science · doi:10.1007/s13201-025-02698-6 · Cited by 4
Reis, M., Serôdio, C., & Branco, F. (2026) · Electronics · doi:10.3390/electronics15020364 · Cited by 3
Smart Healthcare Monitoring Through Federated IoT Networks and Privacy-Preserving Deep Learning
Chaudhary, A. K., Kurada, S. B., Mogili, V. B., Patel, R. B., & Nandan, D. (2025) · IEEE International Conference on Advanced Computing Technologies (ICACT) · doi:10.1109/icact67549.2025.11349724 · Cited by 3
“Because raw data is noisy and has unimportant oscillations, it's filtered using Butterworth filters to remove undesired frequency components to improve signal quality [21-23].”
Anomaly Detection in EVCS Using Federated Learning With Auto-Optimized Edge Models
Hussain, A., Yadav, A., & Ravikumar, G. (2026) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2026.3661521 · Cited by 4
“FL has been widely promoted as a privacy-preserving machine learning approach for distributed and sensitive data sources [6].”
Hafid, A., Hocine, R., Guezouli, L., & Abdessemed, M. R. (2024) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais62114.2024.10541145 · Cited by 6
“Two key paradigms dominate this fast-growing discipline: Centralized FL (CFL) and Decentralized FL (DFL) [1] In contrast, in CFL, a central server coordinates the learning process, distributing a global model to local devices for decentralized updates.”
BackgroundA review in advanced digital signal processing systems
Mugumya, A., Akankunda, J., Matsiko, E., & Buhari, M. D. (2024) · KIU journal of science engineering and technology · doi:10.59568/kjset-2024-3-1-14 · Cited by 3
DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
Saadati, N., Pham, M., Saleem, N., Waite, J. R., Balu, A., Jiang, Z., Hegde, C., & Sarkar, S. (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/cvpr52733.2024.02598 · Cited by 12
“Faced with various large-scale deep learning tasks [5, 19, 40], researchers and practitioners have made considerable efforts to advance numerous decentralized training algorithms [6].”
BackgroundA Reliable Federated Learning Server Rotation Algorithm in IoV
Cai, X., Yang, J., Chang, T., Fu, Y., Yu, F. R., Cheng, N., Li, C., & Hui, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3528013 · Cited by 5
“Some works refer to the concept of complete decentralization, combining blockchain with FL or designing communication topologies to alleviate the overdependence on central servers in the FL process [17].”
Guan, G., Zhi, T., Cai, H., Cao, Y., & Xie, H. (2024) · IEEE International Conference on Computer and Communication Engineering Technology (CCET) · doi:10.1109/ccet62233.2024.10838122 · Cited by 3
Decentralized Federated Learning for Wireless Traffic Prediction
Zhang, H., Huang, S., Zhou, X., Zhang, C., & Jia, J. (2025) · IEEE Communications Letters · doi:10.1109/lcomm.2025.3553678 · Cited by 3
“To address this, federated learning (FL)- based methods were proposed [4], [5], [6].”
Boosting Asynchronous Decentralized Learning with Model Fragmentation
Biswas, S., Kermarrec, A.-M., Marouani, A., Pires, R. P., Sharma, R. K., & de Vos, M. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714872 · Cited by 12
“While the focus on DL has been surging due to its wide range of applicability [7], most existing works in DL consider a synchronous system without the presence of stragglers , i . e ., nodes with slower compute or communication speeds than others [9, 12, 18, 39, 43, 54].”
Trustworthy and Responsible LLM
Ogbuokiri, B. (2025) · Springer eBooks · doi:10.1007/978-981-95-3658-0_51 · Cited by 4
Dang, X.-T., Nguyen, H. V., & Shin, O. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3588353 · Cited by 6
“Federated learning (FL) was introduced to address these challenges by training models across distributed devices within the control of a single centralized point, called the server [2], [7].”
Adaptive Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks
Yan, Z., Li, D., Sun, Q., Niyato, D. T., & Quek, T. Q. S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3611075 · Cited by 5
Asynchronous Federated Learning Technique for Latency Reduction in STAR-RIS Enabled VRCS
Chaudhary, S., Budhiraja, I., Chaudhary, R., Kumar, N., & Biswas, S. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161820 · Cited by 3
“P ROPOSED S OLUTION USING F EDERATED L EARNING FL is a procedure that permits AI models to be produced jointly by scattered devices while maintaining the secrecy of data [18].”
ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes
Sánchez, P. M. S., Beltrán, E. T. M., Llamas, M. F., Bovet, G., Pérez, G. M., & Celdrán, A. H. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161228 · Cited by 3
“Building upon the foundations of FL, Decentralized Federated Learning (DFL) has been proposed as a natural progression of FL, facilitating collaboration among distributed nodes without a central server [2].”
Self-citationG ist - Optimizing Segmentation for Decentralized Federated Learning on Tiny Devices
Asadi, N., Bengu, H. İ., Wulfert, L., Wöhrle, H., & Kellerer, W. (2025) · doi:10.1145/3737899.3768527 · Cited by 3
Fedstellar: A Platform for Training Models in a Privacy-preserving and Decentralized Fashion
Beltrán, E. T. M., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/838 · Cited by 3
Self-citationJiang, X., Gu, R., & Zhan, H. (2024) · Electronic Research Archive · doi:10.3934/era.2024079 · Cited by 4
Parida, A., Anwar, S. M., Patel, M. P., Blom, M., Einat, T. T., Tonetti, A., Baror, Y., Dayan, I., & Linguraru, M. G. (2024) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.3008757 · Cited by 3
Advancing Research Reproducibility in Machine Learning through Blockchain Technology
Filatovas, E., Stripinis, L., Orts, F. J., & Paulavičius, R. (2024) · Informatica · doi:10.15388/24-infor553 · Cited by 10
Towards Opportunistic Federated Learning Using Independent Subnetwork Training
Romero, V., Matsui, T., Matsuda, Y., Suwa, H., & Yasumoto, K. (2024) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp61445.2024.00044 · Cited by 3
“Decentralized federated learning (DFL) [2] was proposed to address the limitations imposed by the central orchestrator.”
InfluentialJi, C., Heusdens, R. R., Maag, S., & Li, Q. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888257 · Cited by 8
“Centralized FL (CFL), which relies on a central server for node coordination, is widely adopted but suffers from high bandwidth demands [7], [8] and introduces risks such as single points of failure [2].”
SecFedDNN: A Secure Federated Deep Learning Framework for Edge–Cloud Environments
Alamir, R. H., Noor, A., Almukhalfi, H. M., Almukhlifi, R., & Noor, T. H. (2025) · Systems · doi:10.3390/systems13060463 · Cited by 5
Connectivity Enrichment for Decentralized Federated Learning Networks with Teleportation
Wang, X., Chen, Y., Ye, Q. J., & D, O. A. D. (2025) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps65812.2025.11152750 · Cited by 3
Kumar, M. A., Mohammed, A., Sumanth, S., & Sivanantham, V. (2024) · Wiley eBooks · doi:10.1002/9781394219230.ch14 · Cited by 3
A crowdsensing intrusion detection dataset for decentralized federated learning models
Feng, C., Celdrán, A. H., Han, J., Ren, H., Cheng, X., Zeng, Z., Kräuter, L., Bovet, G., & Stiller, B. (2026) · Scientific Data · doi:10.1038/s41597-026-07155-w · Cited by 3
“By removing the client-server hierarchy and adopting peer-to-peer topologies, DFL enables each node to act both as a learner and as an aggregator 4 .”
Self-citationTowards a Federated Intrusion Detection System based on Neuromorphic Computing
Lofù, D., Sorino, P., Noia, T. D., & Sciascio, E. D. (2024) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech61897.2024.10612534 · Cited by 4
“As a typical FL system [25], includes a group of N Clients Specifically, In round r , the gradients ∆ M ( c ) r from a subset of participating Clients P r ( N ) are transmitted to the BS.”
BackgroundLoss-Based Decentralized Federated Learning for Robust IoT Intrusion Detection System
Putra, M. A. P., Utami, N. W., Putra, I. G. J. E., Karna, N. B. A., Rahmawati, T., Shiddiq, R. W., Zainudin, A., & Sampedro, G. A. (2024) · IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT) · doi:10.1109/iaict62357.2024.10617474 · Cited by 2
Liu, T., Wu, H., Sun, X., Niu, C., & Yin, H. (2024) · Electronics · doi:10.3390/electronics13214187 · Cited by 2
Practical Federated Learning without a Server
Dhasade, A., Kermarrec, A.-M., Lavoie, E., Pouwelse, J. A., Sharma, R. K., & de Vos, M. (2025) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3721146.3721938 · Cited by 8
Zhao, S., Zheng, X., & Chen, J. (2025) · Electronics · doi:10.3390/electronics14081541 · Cited by 5
Decentralized Federated Learning towards Communication Efficiency, Robustness, and Personalization
Zhang, A., Zhao, P., Lu, W., & Zhang, G. (2025) · ACM Transactions on Sensor Networks · doi:10.1145/3730587 · Cited by 7
MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT
Chen, Z., Zhang, X., Wang, S., & Wang, Y. (2025) · Entropy · doi:10.3390/e27040439 · Cited by 2
Oliveira, R. R., Silva, W. R. S. E., Freitas, L. A., & Oliveira-Jr, A. (2025) · Annals of Telecommunications · doi:10.1007/s12243-025-01089-x · Cited by 2
Core Concepts of Federated Learning
Tabrizchi, H., & Aghasi, A. (2025) · SpringerBriefs in computer science · doi:10.1007/978-3-031-86592-3_2 · Cited by 2
Federated Learning for Detecting Anomaly in IoT Networks
Tomar, V., Jain, V. K., Yadav, A. K., & Shukla, S. S. P. (2025) · doi:10.1109/icsc64553.2025.10967664 · Cited by 3
“The combined updates provide a global model that is improved while keeping clients datasets confidential [18].”
InfluentialTRANSFORMATIVE APPLICATIONS OF AI IN HEALTHCARE AND PHARMACEUTICAL INNOVATION
JASMINE, P., IBRAHIM, A., Siddiq, S., DHANURSHRA, A., NIRMALA, M., & BASHA, S. S. (2025) · International Journal of Applied Pharmaceutics · doi:10.22159/ijap.2025v17i3.52719 · Cited by 3
“Federated learning enhances data privacy by training models across decentralized datasets, improving AI robustness with real-world data [191, 192].”
Decentralized Federated Averaging via Random Walk
Wang, C., Wei, Z., Liu, L., Deng, Q., Wu, Y., Niu, Y., Pang, Y., & Feng, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3569423 · Cited by 5
“More details on DFL can be found in [29], while the latest advancements, additional applications, and outstanding issues are discussed in [30], [31], and [32].”
Towards efficient compression and communication for prototype-based decentralized learning
Fernández-Piñeiro, P., Fernández‐Veiga, M., Redondo, R. P. D., Vilas, A. F., & Soto, M. G. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113270 · Cited by 3
Amarasinghe, A., Siriwardhana, Y., Hewa, T. M., & Ylianttila, M. (2025) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit63408.2025.11037134 · Cited by 2
On the Adoption of Distributed Intelligence Toward 6G Networks
Vandikas, K., Larsson, H., İckin, S., Riaz, H., Temesgene, D. A., Shokri‐Ghadikolaei, H., Raizer, K., Öhlén, P., Roeland, D., & Palaios, A. (2025) · IEEE Access · doi:10.1109/access.2025.3600070 · Cited by 2
Def-Ag: An energy-efficient decentralized federated learning framework via aggregator clients
Park, J., Woo, S., & Lee, J. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108114 · Cited by 3
Wang, J., Wu, Y., Xiong, X., Zhang, Y., Lv, Z., Ghoneim, A., & Zhao, H. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3608003 · Cited by 2
“Although effective, these schemes still rely on a central server, introducing single-point failures and network bottlenecks [20].”
Channel-Distortion-Agnostic Specific Emitter Identification Based on Decentralized Learning
Liu, Y., Xie, S., Sun, X., Fu, X. G., & Gui, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3612404 · Cited by 3
Efficient privacy-preserving federated learning with encrypted-domain knowledge distillation
Huang, W., Yu, P., & Yao, Q. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111752 · Cited by 2
Gulati, S., Guleria, K., Goyal, N., & Dogra, A. (2025) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/0115734056400866250923175325 · Cited by 4
PRISAM: Efficient Personalization via BN Masks in Heterogeneous Decentralized Federated Learning
Chang, S., Wang, X., Hao, Y., Li, D., Liang, G., Zhu, H., & Li, B. (2025) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs63083.2025.00083 · Cited by 2
“Decentralized FL (DFL) [6] [7] removes the central server, allowing devices to collaborate directly in a peer-to-peer (P2P) manner.”
Hao, Z., Zhang, B., & Li, H. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758154 · Cited by 4
“Federated learning has recently emerged as a promising decentralized machine learning paradigm that enables collaborative training without raw data exchange, thus addressing privacy and governance challenges inherent to multimedia data sharing [10].”
Local Data Quantity-Aware Weighted Averaging for Federated Learning with Dishonest Clients
Wu, L., Jin, Y., Hao, K., & Yu, H. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209071 · Cited by 2
“FL can be classified into centralized FL [7], [8], which involves a central node server, and decentralized FL [9], which does not.”
Adaptive Clustering-Enabled Large-Scale Decentralized Federated Learning
Tang, J., Liang, X., Siew, M., & Quek, T. Q. S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3630332 · Cited by 3
Wani, R. U. Z., & Can, Ö. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70432 · Cited by 6
CO-DEFEND: Continuous decentralized federated learning for secure DoH-based threat detection
Cajaraville-Aboy, D., Moure-Garrido, M., Beis-Penedo, C., García-Rubio, C., Díaz-Redondo, R. P., Campo, C., Vilas, A. F., & Fernández‐Veiga, M. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111961 · Cited by 7
Fully-Distributed Fairness-Aware Federated Learning
Im, C., & Kim, J. (2025) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps65812.2025.11152720 · Cited by 2
“To address the challenges of this server-based FL, distributed FL (DFL) has been proposed to enhance the overall performance without relying on a central server, by allowing devices to share the aggregation task among themselves [5]– [7].”
Decentralized Federated Learning Over Time-Varying and Heterogeneous Mobile Computing Networks
Li, B., Gao, W., Deng, X., Xie, J. F., Xiong, Z., Siew, M., Guo, B., Mao, S., & Han, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3638598 · Cited by 5
KAFL-HD: Knowledge Alignment in Asynchronous Federated Learning With Heterogeneous Data
Zhi, M., Bi, Y., Cai, L., & Xiang, T. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3647655 · Cited by 2
“Non-IID data can lead to divergent local optima for clients, which causes the update drift and even degraded performance of the global model [4], [5].”
Abbass, W., Abbas, N., Majeed, U., & Hassan, M. E. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08162-1 · Cited by 2
HLF-FSL: A decentralized federated split learning solution for IoT on hyperledger fabric
Beis-Penedo, C., Redondo, R. P. D., Vilas, A. F., Fernández‐Veiga, M., & Pastoriza, F. M. T. (2026) · Array · doi:10.1016/j.array.2026.100685 · Cited by 8
GreenEdge AI: Sustainable federated learning for smart city air quality prediction
Dey, S., Raina, R., Mishra, S., Prasad, A. S., & Ramesh, D. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101081 · Cited by 6
Enhancing security in IoMT using federated TinyGAN for lightweight and accurate malware detection
Durga, S., Shankar, M. G., Daniel, E., & Varghese, B. G. (2026) · Scientific Reports · doi:10.1038/s41598-026-37830-2 · Cited by 2
“One of the key features of federated learning is that the local data never leaves the device 26 .”
The role of artificial intelligence in advancing population-based cancer registration
Ding, S., Liu, M., Wang, H., Song, C., Zhao, L., Yang, Z., Wang, Y., Wang, Y., Cui, H., Liu, Z., et al. (2026) · 中国科学通报:英文版 · doi:10.1016/j.scib.2026.02.012 · Cited by 2
Decentralized Federated Learning with Multimodal Prototypes for Heterogeneous Data
Beltrán, E. T. M., Bovet, G., Pérez, G. M., & Celdrán, A. H. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104251 · Cited by 4
Self-citationDP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models
Xu, H., Shrestha, S., Chen, W., Li, Z., & Cai, Z. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00089 · Cited by 19
“Federated learning (FL) enables decentralized model adaptation by allowing edge devices to train on their local data while only sharing model updates [5], [6].”
Li, A., & Liu, J. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3673201 · Cited by 3
“A. Federated Learning 1) Foundation and Data Heterogeneity Problem of FL: FL is a decentralized machine learning method where multiple clients collaboratively train a global model without sharing their local data [19], [20], [21], [22].”
Privacy Decentralized Online Federated Learning for Smart Healthcare Service Systems
Jiang, L., Ming, X., & Wei, M. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3680310 · Cited by 2
“Classical FL encompasses horizontal, vertical, and transfer learning paradigms, but typically relies on a central server, which introduces a single point of failure and vulnerability to targeted attacks [10], [11], [12], [13].”
Yang, L., Li, S., & Zhu, C. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104393 · Cited by 2
Decentralized semi-federated learning in digital twin-empowered industrial IoT
Chen, F., Wu, X., & Tang, J. (2026) · Digital Communications and Networks · doi:10.1016/j.dcan.2026.04.003 · Cited by 3
When Robotics Meets Distributed Learning: the Federated Learning Robotic Network Framework
Marino, R. A., Carnevale, L., & Villari, M. (2023) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc58397.2023.10218022 · Cited by 3
“FL is introduced in [9] where the authors present a survey of Decentralized Federated Learning (DFL) and its fundamentals in terms of federation architectures, topologies, communication mechanism, security approaches and key performance indicators.”
BackgroundDe-DSI: Decentralised Differentiable Search Index
Neague, P., Gregoriadis, M., & Pouwelse, J. A. (2024) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3642970.3655837 · Cited by 9
“Decentralised federated learning is now becoming a mainstream topic as studied by [13].”
BackgroundFed-NAD: Backdoor Resilient Federated Learning via Neural Attention Distillation
Ma, H., Qi, S., Yao, J., Yuan, Y., Zou, Y., & Yu, D. (2024) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/ids62739.2024.00009 · Cited by 2
“Different from centralized FL, decentralized FL paradigm without a parameter server introduces heightened challenges for backdoor defense [38].”
BackgroundKeeping Verticals’ Sovereignty During Application Migration in Continuum
Kotulski, Z., Nowak, T. W., Sepczuk, M., Bocianiak, K., Pawlikowski, T., Podlasek, A., & Wary, J.-P. (2024) · Journal of Network and Systems Management · doi:10.1007/s10922-024-09843-7 · Cited by 2
“Among the technologies supporting cloud computing operations, artificial intelligence comes to the fore today [37].”
Decentralized Incremental Federated Learning with Echo State Networks
Pompei, G., Dazzi, P., Caro, V. D., & Gallicchio, C. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650756 · Cited by 3
“To tackle these issues, Decentralized Federated Learning (DFL) was proposed [16].”
BackgroundPrivacy-Preserving Parameter Aggregation Scheme Based on Two Leaders for Federated Learning
Wang, W., Lian, Z., Li, T., Sakurai, K., & Su, C. (2024) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/cyberscitech64112.2024.00029 · Cited by 3
“Federated learning enables clients to train their own local models using raw data that cannot be shared due to privacy concerns [4].”
Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data
Feng, C., Celdrán, A. H., Zeng, Z., Ye, Z., von der Assen, J., Bovet, G., & Stiller, B. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825953 · Cited by 4
“In response, the Decentralized FL (DFL) paradigm has garnered increasing attention, as it eliminates the client-server boundary, thereby significantly enhancing the system’s stability and robustness [3].”
Self-citation
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.