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]”
MethodThe MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
Deng, L. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2211477 · Cited by 4,836 · cited 10×
“[52] 2021 A method for D2D network in industrial IoT devices for improving the convergence of communications Cross-device Decentralized Real MobileNet FedAvg (consensus) Asynchronous Random MNIST [172]”
BackgroundMethodInfluentialWang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616
The MovieLens Datasets: History and Context
Harper, F. M., & Konstan, J. A. (2016) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2827872 · Cited by 3,907 · 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: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766 · cited 2×
“Federation Models KPIs Evaluation of the federated models of each node of the network considering their performance and trustworthiness [16], [89]–[93]”
MethodDistributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719 · cited 1×
“Each node maintains estimates of the optimal optimization step on information concerning its cost function and exchanges these estimates directly with the other nodes in the network [129].”
BackgroundTschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
Friendship and mobility: user movement in location-based social networks
Cho, E., Myers, S. A., & Leskovec, J. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020579 · Cited by 2,903 · cited 1×
“[72] 2022 Decentralized recommender system based on the principles of gossip learning Cross-device Decentralized Simulation GMF PRME-G FedAvg FedFast Reptile Synchronous Scheduling Foursqueare-NYC [193] Gowalla-NYC [194] MovieLens [195] [73] 2022 Gossip-based system to maximize social awareness among nodes, improving…”
MethodFederated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565 · cited 1×
“In this sense, in 2020, Lim et al. [23] reviewed the use of CFL in mobile networks using different end-user applications, while in 2021, researchers such as Nguyen et al. [24] and Khan et al. [25] examined the application of FL in more complex scenarios involving different heterogeneous IoT devices.”
Towards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334 · cited 2×
“To address this problem, over-selection techniques could increase participant selection but also lead to resource waste and selection bias [11].”
BackgroundPollard, T. J., Johnson, A. E. W., Raffa, J. D., Celi, L. A., Mark, R. G., & Badawi, O. (2018) · Scientific Data · doi:10.1038/sdata.2018.178 · Cited by 1,993
Riley, G. F., & Henderson, T. R. (2010) · Modeling and Tools for Network Simulation · doi:10.1007/978-3-642-12331-3_2 · Cited by 1,516 · cited 3×
“[206] 2020 Federated learning-based security architecture for jamming attack detection for FANET Cross-device Centralized Decentralized Simulation Three-layered NN FedAvg Asynchronous Random CRAWDAD [] NS3 FANET [208]”
MethodInfluentialFederated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503 · cited 1×
“In this sense, in 2020, Lim et al. [23] reviewed the use of CFL in mobile networks using different end-user applications, while in 2021, researchers such as Nguyen et al. [24] and Khan et al. [25] examined the application of FL in more complex scenarios involving different heterogeneous IoT devices.”
N-BaIoT—Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders
Meidan, Y., Bohadana, M., Mathov, Y., Mirsky, Y., Shabtai, A., Breitenbacher, D., & Elovici, Y. (2018) · IEEE Pervasive Computing · doi:10.1109/mprv.2018.03367731 · Cited by 1,483 · cited 1×
“[124] 2021 Anomaly detection ML models in non-IID scenarios, including mechanisms to locally rebalance training datasets Cross-device Decentralized Simulation Four-layered FCNN P2PK-SMOTE Synchronous Asynchronous Random N-BaIoT [180]”
MethodA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480 · cited 2×
“GBDTs have been especially popular recently due to their superior performance in many classification and regression tasks [26].”
BackgroundEXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
Shi, W., Ling, Q., Wu, G., & Yin, W. (2015) · SIAM Journal on Optimization · doi:10.1137/14096668x · Cited by 1,261 · cited 1×
“Some examples are Decentralized Gradient Descent (DGD) [104], decentralized Alternating Direction Method of Multipliers (ADMM) [105], EXTRA [106], and ADMM based on Jacobi-Proximal [107].”
Differentially Private Federated Learning: A Client Level Perspective
Geyer, R. C., Klein, T., & Nabi, M. (2017) · arXiv · doi:10.48550/arxiv.1712.07557 · Cited by 1,052 · cited 1×
“• Encryption mechanisms while preserving reliability between participants [45], [83] Key Performance Indicators Federation Nodes KPIs • Measure the node performance considering the heterogeneity and dynamism of the network [13], [84]”
BackgroundLEAF: A Benchmark for Federated Settings
Caldas, S., Duddu, S. M. K., Wu, P., Li, T., Konečný, J., McMahan, H. B., Smith, V., & Talwalkar, A. (2018) · arXiv · doi:10.48550/arxiv.1812.01097 · Cited by 894 · cited 1×
“Along the same lines, LEAF [147] provides only benchmark functionality of the deployed architectures.”
BackgroundAlsaedi, A., Moustafa, N., Tari, Z., Mahmood, A., & Anwar, A. (2020) · IEEE Access · doi:10.1109/access.2020.3022862 · Cited by 892 · cited 1×
“The authors used TON_IoT [186] and LITNET-2020 [187] to validate the robustness and efficiency of the framework over different cyberattack detection approaches.”
MethodFederated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges
Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3090430 · Cited by 892
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. (2021) · Deakin Research Online (Deakin University) · Cited by 889
Swarm Learning for decentralized and confidential clinical machine learning
Warnat-Herresthal, S., Schultze, H., Shastry, K. L., Manamohan, S., Mukherjee, S., Garg, V., Sarveswara, R., Händler, K., Pickkers, P., Aziz, N. A., et al. (2021) · Nature · doi:10.1038/s41586-021-03583-3 · Cited by 884 · cited 2×
“[158] 2021 Facilitate the integration of any medical data from any data owner worldwide without violating privacy laws Cross-silo Decentralized Real Custom model Custom aggregator Asynchronous Scheduling PBMC transcriptome [159] Chest X-ray [160]”
BackgroundQSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
Alistarh, D., Grubic, D., Li, J., Tomioka, R., & Vojnović, M. (2016) · London School of Economics and Political Science Research Online (London School of Economics and Political Science) · doi:10.48550/arxiv.1610.02132 · Cited by 859
Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs
Yang, D., Zhang, D., Zheng, V. W., & Yu, Z. (2015) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2014.2327053 · Cited by 846
On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
Shi, W., Ling, Q., Yuan, K., Wu, G., & Yin, W. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2304432 · Cited by 820 · cited 1×
“Some examples are Decentralized Gradient Descent (DGD) [104], decentralized Alternating Direction Method of Multipliers (ADMM) [105], EXTRA [106], and ADMM based on Jacobi-Proximal [107].”
MethodBlockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles
Lu, Y., Huang, X., Zhang, K., Maharjan, S., & Zhang, Y. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2973651 · Cited by 733 · cited 1×
“This mechanism has been utilized in several studies, such as [219] and [220].”
MethodAutomatic Tuberculosis Screening Using Chest Radiographs
Jaeger, S., Karargyris, A., Candemir, S., Folio, L., Siegelman, J., Callaghan, F., Xue, Z., Palaniappan, K., Singh, R. K., Antani, S., et al. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2284099 · Cited by 678 · cited 1×
“[169] 2022 Exploit concepts from experience repetition and adversarial generation research Cross-device Centralized Decentralized Simulation GAN FedAvg FedProx FedBN Synchronous Asynchronous Random X-ray data [170], [171] HAM10000 [172]”
BackgroundFederated learning with hierarchical clustering of local updates to improve training on non-IID data
Briggs, C., Fan, Z., & Andras, P. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207469 · Cited by 676 · cited 1×
“Furthermore, since nodes within a cluster share similar data distributions, individually trained cluster models may be less generic and robust than models exposed to global data distributions [57].”
BackgroundLung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid Registration
Candemir, S., Jaeger, S., Palaniappan, K., Musco, J. P., Singh, R. K., Xue, Z., Karargyris, A., Antani, S., Thoma, G., & McDonald, C. J. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2290491 · Cited by 674 · cited 1×
“[173] 2022 Exploit concepts from experience repetition and adversarial generation research Cross-device Centralized Decentralized Simulation GAN FedAvg FedProx FedBN Synchronous Asynchronous Random X-ray data [174], [175] HAM10000 [176]”
BackgroundCOVID-CT-Dataset: A CT Scan Dataset about COVID-19
Yang, X., He, X., Zhao, J., Zhang, Y., Zhang, S., & Xie, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13865 · Cited by 673 · cited 1×
“[2] 2022 Collaboratively training between healthcare devices for creating a robust model without raw data exchange Cross-device Decentralized Simulation 3D CNN Custom FedAvg (RingAVG) Synchronous Asynchronous Random COVID-19 CT [169] Eye Disease [170] Skin Cancer [171] [21] 2022 Ring topology for DGM to ensure securit…”
MethodSecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2021) · IEEE Intelligent Systems · doi:10.1109/mis.2021.3082561 · Cited by 669 · cited 2×
“For privacy preservation, SecureBoost [56] builds multi-part reinforcement trees with an encryption strategy between different nodes.”
BackgroundMethodSecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2019) · arXiv · doi:10.48550/arxiv.1901.08755 · Cited by 668
Multi-Scale attributed node embedding
Rozemberczki, B., Allen, C., & Sarkar, R. (2021) · Journal of Complex Networks · doi:10.1093/comnet/cnab014 · Cited by 640
On the Convergence of Decentralized Gradient Descent
Yuan, K., Ling, Q., & Yin, W. (2013) · arXiv · doi:10.48550/arxiv.1310.7063 · Cited by 635
On the Convergence of Decentralized Gradient Descent
Yuan, K., Ling, Q., & Yin, W. (2016) · SIAM Journal on Optimization · doi:10.1137/130943170 · Cited by 633 · cited 1×
“Some examples are Decentralized Gradient Descent (DGD) [104], decentralized Alternating Direction Method of Multipliers (ADMM) [105], EXTRA [106], and ADMM based on Jacobi-Proximal [107].”
MethodCommunication-efficient federated learning via knowledge distillation
Wu, C., Wu, F., Lyu, L., Huang, Y., & Xie, X. (2022) · Nature Communications · doi:10.1038/s41467-022-29763-x · Cited by 618 · cited 1×
“• Use of meta-learning, multitasking, and federated distillation in federation tasks [91], [111]–[114]”
BackgroundFederated Learning With Blockchain for Autonomous Vehicles: Analysis and Design Challenges
Pokhrel, S. R., & Choi, J. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.2990686 · Cited by 531 · cited 1×
“This mechanism has been utilized in several studies, such as [219] and [220].”
MethodSplit learning for health: Distributed deep learning without sharing raw patient data
Vepakomma, P., Gupta, O., Swedish, T., & Raskar, R. (2018) · arXiv · doi:10.48550/arxiv.1812.00564 · Cited by 513
Parallel Multi-Block ADMM with o(1 / k) Convergence
Deng, W., Lai, M.-J., Peng, Z., & Yin, W. (2017) · Journal of Scientific Computing · doi:10.1007/s10915-016-0318-2 · Cited by 455 · cited 1×
“Some examples are Decentralized Gradient Descent (DGD) [104], decentralized Alternating Direction Method of Multipliers (ADMM) [105], EXTRA [106], and ADMM based on Jacobi-Proximal [107].”
Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing
Qu, Y., Gao, L., Luan, T. H., Xiang, Y., Yu, S., Li, B., & Zheng, G. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2977383 · Cited by 451 · cited 1×
“In this sense, time, cycles, and temperature are considered [87].”
BackgroundLarge scale distributed neural network training through online distillationPreprint
Anil, R., Pereyra, G., Passos, A., Ormándi, R., Dahl, G. E., & Hinton, G. E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.03235 · Cited by 440 · cited 1×
“All this offers less computation time and energy consumption in the federated node [113].”
BackgroundHuang, L., Shea, A. L., Qian, H., Masurkar, A., Deng, H., & Liu, D. (2019) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103291 · Cited by 437
EMNIST: an extension of MNIST to handwritten letters
Cohen, G., Afshar, S., Tapson, J. C., & André, V. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05373 · Cited by 419 · cited 3×
“Cross-device Centralized Decentralized Simulation MobileNetv2 BLSTM Custom algorithm Synchronous Asynchronous Random CIFAR-10 [152] Avito [200] IMDb [201] [202] 2023 Personalized and fully decentralized FL algorithm using knowledge distillation Cross-device Decentralized Simulation Three-layered NN CNN Custom algorith…”
MethodThe Non-IID Data Quagmire of Decentralized Machine LearningPreprint
Hsieh, K., Phanishayee, A., Mutlu, O., & Gibbons, P. B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00189 · Cited by 414 · cited 1×
“One option presented in the literature is to continue aggregating them at a higher level [117], while another option is to accept the presence of different federated models based on the network topology and characteristics of the nodes [118].”
BackgroundLian, X., Zhang, C., Zhang, H., Hsieh, C., Zhang, W., & Liu, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.09056 · Cited by 395 · cited 1×
“Other studies, such as [140], have shown that decentralized SGD can out-perform centralized approaches in low-bandwidth networks.”
BackgroundDecentralized Federated Averaging
Sun, T., Li, D., & Wang, B. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3196503 · Cited by 388 · cited 2×
“better convergence rate and communication efficiency than DSGD [129].”
BackgroundA Blockchained Federated Learning Framework for Cognitive Computing in Industry 4.0 Networks
Qu, Y., Pokhrel, S. R., Garg, S., Gao, L., & Xiang, Y. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3007817 · Cited by 340 · cited 1×
“Following the same direction, the authors of [181] applied cognitive computing in a simulated industrial scenario.”
BackgroundLearning in the Air: Secure Federated Learning for UAV-Assisted Crowdsensing
Wang, Y., Su, Z., Zhang, N., & Benslimane, A. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2020.3014385 · Cited by 323 · cited 3×
“The increase in the number of papers using DFL in different scenarios: healthcare [2], [21], Industry 4.0 [17], mobile services [18], military [19], and vehicles [22] motivate the need to identify the fundamental elements of DFL and review the work done to date.”
BackgroundMethodInfluentialFedML: A Research Library and Benchmark for Federated Machine Learning
He, C., Li, S., So, J., Zeng, X., Zhang, M., Wang, H., Wang, X., Vepakomma, P., Singh, A., Qiu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13518 · Cited by 314 · cited 1×
“Other frameworks, such as FederatedScope [145] and FedML [146], allow lower-level management of the deployed architecture.”
MethodRodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296 · cited 1×
“the attack (training or evaluation time) and frequency (one-shot or multiple) [124].”
BackgroundBlockchain-enabled Federated Learning: A Survey
Qu, Y., Uddin, M. P., Gan, C., Xiang, Y., Gao, L., & Yearwood, J. (2023) · ACM Computing Surveys · doi:10.1145/3524104 · Cited by 286 · cited 1×
“In contrast, most of the works covering DFL approaches focus on analyzing the use of Distributed Ledger Technology (DLT) technologies (e.g., Blockchain) [30].”
BackgroundLu, Y., Huang, X., Zhang, K., Maharjan, S., & Zhang, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3015772 · Cited by 283 · cited 2×
“[186] conducted a theoretical analysis to enhance communication security and protect data privacy in Digital Twin Edge Networks (DITENs).”
BackgroundMethodFusion of Federated Learning and Industrial Internet of Things: A survey
Boobalan, P., Ramu, S. P., Pham, Q.-V., Dev, K., Pandya, S., Maddikunta, P. K. R., Gadekallu, T. R., & Huynh-The, T. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109048 · Cited by 280
Qsparse-local-SGD: Distributed SGD with quantization, sparsification, and local computations
Basu, D., Data, D., Karakus, C., & Diggavi, S. N. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2985917 · Cited by 256 · cited 4×
“Many DFL studies are based on Stochastic Gradient Descent (SGD), which can be used to train NNs [110], [113].”
BackgroundMethodInfluentialPySyft: A Library for Easy Federated Learning
Ziller, A., Trask, A., Lopardo, A., Szymkow, B., Wagner, B., Bluemke, E., Nounahon, J.-M., Passerat-Palmbach, J., Prakash, K., Rose, N., et al. (2021) · Studies in Computational Intelligence · doi:10.1007/978-3-030-70604-3_5 · Cited by 246 · cited 1×
“Other frameworks, such as PySyft [144], provide interfaces for developers to implement their training algorithm.”
MethodIoT-23: A labeled dataset with malicious and benign IoT network traffic
García, S., Parmisano, A., & Erquiaga, M. J. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4743745 · Cited by 236
IoT-23: A labeled dataset with malicious and benign IoT network traffic
García, S., Parmisano, A., & Erquiaga, M. J. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4743746 · Cited by 233 · cited 2×
“Another study, conducted by Lian and Su [179], discussed a similar approach with the IoT23 dataset [180], obtaining a model convergence 30% faster than in the previous study with an increase of only 3% in the overhead”
MethodResultLi, J., Shao, Y., Wei, K., Ding, M., Ma, C., Shi, L., Han, Z., & Poor, H. V. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3138848 · Cited by 230 · cited 1×
“Similarly, BLADE-FL [151] uses Blockchain Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodBlockchain-Empowered Decentralized Horizontal Federated Learning for 5G-Enabled UAVs
Feng, C., Liu, B., Yu, K., Goudos, S. K., & Wan, S. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3116132 · Cited by 213 · cited 15×
“HFL is the most commonly employed method in DFL, as it involves sample federation and is applicable when there are many overlapping features and few overlapping nodes, typically associated with cross-device scenarios.”
BackgroundMethodInfluentialBrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
Roy, A. G., Siddiqui, S., Pölsterl, S., Navab, N., & Wachinger, C. (2019) · arXiv · doi:10.48550/arxiv.1905.06731 · Cited by 212 · cited 1×
“BrainTorrent [148] is an FL framework without a central server explicitly aimed at medical applications.”
Communication Compression for Decentralized Training
Tang, H., Gan, S., Zhang, C., Zhang, T., & Liu, J. (2018) · arXiv · doi:10.48550/arxiv.1803.06443 · Cited by 206
Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
Joshi, M., Pal, A., & Sankarasubbu, M. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3533708 · Cited by 203 · cited 2×
“Other articles, such as [29], reviewed the applicability in specific medical scenarios, discussing sensitive data privacy mechanisms.”
BackgroundFedGroup: Efficient Federated Learning via Decomposed Similarity-Based Clustering
Duan, M., Liu, D., Ji, X., Liu, R. P., Liang, L., Chen, X., & Tan, Y. (2021) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00042 · Cited by 203 · cited 1×
“this regard, the literature addresses two approaches: similaritybased clusters [119] and proxy-based clusters [45].”
BackgroundA training-integrity privacy-preserving federated learning scheme with trusted execution environment
Chen, Y., Luo, F., Li, T., Xiang, T., Liu, Z., & Li, J. (2020) · Information Sciences · doi:10.1016/j.ins.2020.02.037 · Cited by 188 · cited 1×
“One such approach is based on deploying a Trusted Execution Environment (TEE) [77], such as Intel SGX processors, which can protect the code and data loaded inside it.”
MethodDecentralized Federated Learning: A Segmented Gossip ApproachPreprint
Hu, C., Jiang, J., & Wang, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07782 · Cited by 184 · cited 1×
“Then, this subsection presents two different decentralized communications mechanisms: peer-to-peer (P2P) [62] and gossip [121].”
BackgroundDecentralized Federated Learning With Unreliable Communications
Ye, H., Liang, L., & Li, G. Y. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3152445 · Cited by 184
Opportunities of Federated Learning in Connected, Cooperative, and Automated Industrial Systems
Savazzi, S., Nicoli, M., Bennis, M., Kianoush, S., & Barbieri, L. (2021) · IEEE Communications Magazine · doi:10.1109/mcom.001.2000200 · Cited by 181 · cited 2×
“In [8], the authors discussed the opportunities and applications of DFL in automated and networked industrial systems supported by Device-to-Device (D2D) communications.”
BackgroundMethodDecentralized P2P Federated Learning for Privacy-Preserving and Resilient Mobile Robotic Systems
Zhou, X., Liang, W., Wang, K. I.-K., Yan, Z., Yang, L. T., Wei, W., Ma, J., & Jin, Q. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.004.2200381 · Cited by 179 · cited 1×
“robotics, DFL enables asynchronous knowledge sharing and task coordination [157].”
BackgroundDai, R., Shen, L., He, F., Tian, X., & Tao, D. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.00187 · Cited by 175 · cited 4×
“DisPFL [38] Windows Linux MacOS Cross-device Decentralized FedAvg Ditto FOMO Sub-FedAvg P2P ✗ Time series Images Simulation Real ✗”
BackgroundMethodInfluentialGossipFL: A Decentralized Federated Learning Framework With Sparsified and Adaptive Communication
Tang, Z., Shi, S., Li, B., & Chu, X. (2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3230938 · Cited by 168
Decentralized Collaborative Learning of Personalized Models over NetworksPreprint
Vanhaesebrouck, P., Bellet, A., & Tommasi, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05202 · Cited by 167 · cited 1×
“These models optimize metrics for each task and generate a corresponding output [91].”
MethodDecentralized Federated Learning via Mutual Knowledge Transfer
Li, C., Li, G., & Varshney, P. K. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3078543 · Cited by 167 · cited 1×
“Finally, depending on the nature of the problem to be solved and the organization of data (features and samples) among nodes, DFL is usually divided into three types: Horizontal Federated Learning (HFL) [42], Vertical Federated Learning (VFL) [49], and Transfer Federated Learning (TFL) [50].”
BackgroundDecentralized Federated Learning for Healthcare Networks: A Case Study on Tumor Segmentation
Camajori Tedeschini, B., Savazzi, S., Stoklasa, R., Barbieri, L., Stathopoulos, I., Nicoli, M., & Serio, L. (2022) · IEEE Access · doi:10.1109/access.2022.3141913 · Cited by 164 · cited 1×
“Similarly, the authors of [98] focused on medical image prediction for brain tumor segmentation, enabling the collaboration of multiple institutions by sharing their local computational models and training a U-Net model.”
BackgroundDecentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
Koloskova, A., Stich, S. U., & Jaggi, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00340 · Cited by 163 · cited 1×
“However, these methods may decrease accuracy to achieve lower communication costs [74].”
MethodDecentralized learning works: An empirical comparison of gossip learning and federated learning
Hegedűs, I., Danner, G., & Jelasity, M. (2021) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2020.10.006 · Cited by 162 · cited 1×
“The comparison of the DFL approach using gossip communications versus the CFL approach has been extensively studied, with superior performance obtained in the former when a better understanding of model parameters is employed [69].”
MethodDecentralized federated learning through proxy model sharing
Kalra, S., Wen, J., Cresswell, J. C., Volkovs, M., & Tizhoosh, H. R. (2023) · Nature Communications · doi:10.1038/s41467-023-38569-4 · Cited by 160 · cited 2×
“This role is intended to relay the received model parameters to neighboring nodes, allowing different nodes or network topologies to be interconnected [44].”
BackgroundDecentralized Federated Learning: Balancing Communication and Computing Costs
Liu, W., Chen, L., & Zhang, W. (2022) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2022.3151242 · Cited by 158
Semi-Decentralized Federated Learning With Cooperative D2D Local Model Aggregations
Lin, F., Hosseinalipour, S., Azam, S. S., Brinton, C. G., & Michelusi, N. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118344 · Cited by 155 · cited 1×
“Restrictions apply. based on its performance, such as network, computational, or power capacity [47], [48].”
BackgroundBDFL: A Byzantine-Fault-Tolerance Decentralized Federated Learning Method for Autonomous Vehicle
Chen, J.-H., Chen, M.-R., Zeng, G., & Weng, J. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3102121 · Cited by 154 · cited 2×
“The increase in the number of papers using DFL in different scenarios: healthcare [2], [21], Industry 4.0 [17], mobile services [18], military [19], and vehicles [22] motivate the need to identify the fundamental elements of DFL and review the work done to date.”
BackgroundInfluentialDecentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunities
Qu, Y., Dai, H., Zhuang, Y., Chen, J., Dong, C., Wu, F., & Guo, S. (2021) · IEEE Network · doi:10.1109/mnet.001.2100253 · Cited by 152 · cited 1×
“Qu et al. [212] proposed a similar solution, where the authors provided three critical considerations: (i) the average loss achieved by DFL is similar to the one obtained in a centralized approach; (ii) for each UAV, the loss value after 60 rounds is similar to the achieved in the centralized…”
ResultA Decentralized Federated Learning Framework via Committee Mechanism With Convergence Guarantee
Che, C., Li, X., Chen, C., He, X., & Zheng, Z. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3202887 · Cited by 149 · cited 1×
“In this case, [152] presented a serverless framework named Committee Mechanism-based Federated Learning (CMFL), orchestrated by a committee system deploying selection strategies of model parameters during federation.”
MethodFederated learning-based cognitive detection of jamming attack in flying Ad-Hoc network
Mowla, N. I., Tran, N. H., Doh, I., & Chae, K. (2020) · IEEE Access · doi:10.1109/access.2019.2962873 · Cited by 147
Tian, Y., Wang, S., Xiong, J., Bi, R., Zhou, Z., & Bhuiyan, M. Z. A. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3243932 · Cited by 142 · cited 1×
“[177] 2023 Privacy-preserving decentralized approach while supporting efficient communications Cross-silo Decentralized Simulation N/S Custom algorithm Synchronous Random MNIST [172]”
MethodDecentralized federated learning for extended sensing in 6G connected vehicles
Barbieri, L., Savazzi, S., Brambilla, M., & Nicoli, M. (2021) · Vehicular Communications · doi:10.1016/j.vehcom.2021.100396 · Cited by 137 · cited 2×
“Similarly, Barbieri et al. [3] investigated the use of DFL methods to improve the classification of road users (such as pedestrians, cyclists, and vehicles) and objects based on Lidar data.”
BackgroundMethodLITNET-2020: An Annotated Real-World Network Flow Dataset for Network Intrusion Detection
Damasevicius, R., Venckauskas, A., Grigaliunas, S., Toldinas, J., Morkevicius, N., Aleliunas, T., & Smuikys, P. (2020) · Electronics · doi:10.3390/electronics9050800 · Cited by 132 · cited 3×
“[181] 2022 A BoEI framework that integrates an innovative decentralized federated learning for cyberattack detection in IIoT Cross-device Centralized Decentralized Simulation Custom model Fed-Trust Synchronous Asynchronous Random TON_IoT [182] LITNET-2020 [183]”
MethodTrustFed: A Framework for Fair and Trustworthy Cross-Device Federated Learning in IIoT
Rehman, M. H. U., Dirir, A. M., Salah, K., Damiani, E., & Svetinovic, D. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3075706 · Cited by 132 · cited 2×
“To maintain the reputation of the participating devices and ensure that all participants make active and honest contributions to the model, the trustor node i can generate a smart contract with the parameters of the local model, which is validated by a set of trustee nodes j [142].”
MethodTopology-aware Federated Learning in Edge Computing: A Comprehensive Survey
Wu, J., Dong, F., Leung, H., Zhu, Z., Zhou, J., & Drew, S. (2024) · ACM Computing Surveys · doi:10.1145/3659205 · Cited by 130 · cited 1×
“Moreover, the article by Wu et al. [34] provided a comprehensive survey of optimized DFL models and algorithms focusing on network topologies.”
BackgroundDecentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review
Witt, L., Heyer, M., Toyoda, K., Samek, W., & Li, D. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3231363 · Cited by 130
Saraswat, D., Verma, A., Bhattacharya, P., Tanwar, S., Sharma, G., Bokoro, P. N., & Sharma, R. (2022) · IEEE Access · doi:10.1109/access.2022.3161132 · Cited by 127 · cited 1×
“Similarly, other authors explored the applicability of DFL in particular scenarios such as IoV [31], wireless communications [32], or UAV devices [33].”
BackgroundCOLA: Decentralized Linear LearningPreprint
He, L., Bian, Y., & Jaggi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.04883 · Cited by 125 · cited 1×
“DFL,also known as Serverless or Distributed FL, emerged in 2018 to distribute the aggregation of model parameters between the neighboring participants [5].”
BackgroundEdge-Based Communication Optimization for Distributed Federated Learning
Wang, T., Liu, Y., Zheng, X., Dai, H., Weijia Jia, B., & Xie, M. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3083263 · Cited by 124 · cited 4×
“Firstly, DFL improves fault tolerance because nodes constantly update their knowledge about available nodes or those that have ceased communicating [7].”
BackgroundInfluentialFederated Knowledge DistillationPreprint
Seo, H., Park, J., Oh, S., Bennis, M., & Kim, S.-L. (2020) · arXiv.org · doi:10.48550/arxiv.2011.02367 · Cited by 118 · cited 1×
“A decentralized version of this approach has been proposed in [114], where instead of having a pre-trained model to imitate it, each model considers the aggregated knowledge of the remaining participants’ models.”
BackgroundFusionFedBlock: Fusion of blockchain and federated learning to preserve privacy in industry 5.0
Singh, S. K., Yang, L. T., & Park, J. H. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.027 · Cited by 115 · cited 2×
“In this sense, the use of advanced technologies such as 5G [138] or 6G [139] can help reduce communication limitations, improving network bandwidth and enable faster and more efficient data exchange.”
BackgroundInfluentialBlockchain-based Federated Learning for Industrial Metaverses: Incentive Scheme with Optimal AoI
Kang, J., Ye, D., Nie, J., Xiao, J., Deng, X., Wang, S., Xiong, Z., Yu, R., & Niyato, D. T. (2022) · IEEE International Conference on Blockchain (Blockchain) · doi:10.1109/blockchain55522.2022.00020 · Cited by 112 · cited 4×
“[18] 2022 User-defined privacy-preserving framework for industrial metaverses Cross-silo Cross-device Decentralized Simulation N/S Custom FedAvg Asynchronous Scheduling Private”
BackgroundInfluentialIPLS: A Framework for Decentralized Federated Learning
Pappas, C., Chatzopoulos, D., Lalis, S., & Vavalis, M. (2021) · IFIP Networking Conference (IFIP Networking) · doi:10.23919/ifipnetworking52078.2021.9472790 · Cited by 110
FederatedTrust: A solution for trustworthy federated learning
Sánchez, P. M. S., Celdrán, A. H., Xie, N., Bovet, G., Pérez, G. M., & Stiller, B. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.10.013 · Cited by 103
Self-citationFedstellar: A Platform for Decentralized Federated Learning
Beltrán, E. T. M., Gómez, Á. L. P., Feng, C., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122861 · Cited by 103 · cited 1×
“Building on these advancements, Fedstellar [153] offers a versatile platform for DFL training that addresses common limitations in existing frameworks.”
BackgroundSelf-citationFederated reinforcement learning for decentralized voltage control in distribution networks
Liu, H., & Wu, W. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3169361 · Cited by 101 · cited 1×
“However, data originating from a massive number of Internet of Things (IoT) devices are commonly stored in a distributed manner for a wide range of scenarios such as smart grids [1], remote health monitoring [2], or Internet of Vehicles (IoV) [3].”
BackgroundDecentralized Wireless Federated Learning With Differential Privacy
Chen, S., Yu, D., Zou, Y., Yu, J., & Cheng, X. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3145010 · Cited by 100
Lian, Z., Yang, Q., Wang, W., Zeng, Q., Alazab, M., Zhao, H., & Su, C. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3175945 · Cited by 100 · cited 5×
“The increase in the number of papers using DFL in different scenarios: healthcare [3], [24], Industry 4.”
BackgroundMethodInfluentialAccelerating Decentralized Federated Learning in Heterogeneous Edge Computing
Wang, L., Xu, Y., Xu, H., Chen, M., & Huang, L. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3178378 · Cited by 98 · cited 3×
“The increase in the number of papers using DFL in different scenarios: healthcare [2], [21], Industry 4.0 [17], mobile services [18], military [19], and vehicles [22] motivate the need to identify the fundamental elements of DFL and review the work done to date.”
BackgroundMethodInfluentialLatency Optimization for Blockchain-Empowered Federated Learning in Multi-Server Edge Computing
Nguyen, D. C., Hosseinalipour, S., Love, D. J., Pathirana, P. N., & Brinton, C. G. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3213344 · Cited by 93 · cited 1×
“Further approaches, such as [136], implement latency optimization strategies by incorporating Blockchain.”
MethodImproving the Model Consistency of Decentralized Federated LearningPreprint
Shi, Y., Shen, L., Kang, W., Sun, Y. P., Yuan, B., Wang, X., & Tao, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.04083 · Cited by 93 · cited 1×
“To enhance the consistency of models generated by each federation participant, algorithms such as DFedSAM utilize gradient perturbation to produce local flat models with uniformly low loss values [111].”
MethodWalkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization
Mao, X., Yuan, K., Hu, Y., Gu, Y., Sayed, A. H., & Yin, W. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2983167 · Cited by 90 · cited 1×
“These include Random Walk ADMM (WADMM) [134], Parallel Random Walk ADMM (PW-ADMM) [123] and Walk Proximal Gradient (WPG) [135] which are commonly used in increment-based approaches.”
MethodDecentralized Federated Learning for Electronic Health Records
Lu, S., Zhang, Y., & Wang, Y. (2020) · Conference on Information Sciences and Systems · doi:10.1109/ciss48834.2020.1570617414 · Cited by 87 · cited 1×
“The authors of [162] introduced an algorithm to perform local updates during several iterations, enabling communication between nodes and improving communication efficiency for DFL.”
MethodNguyen, T., Dakka, M. A., Diakiw, S. M., VerMilyea, M. D., Perugini, M., Hall, J. M. M., & Perugini, D. (2022) · Scientific Reports · doi:10.1038/s41598-022-12833-x · Cited by 87 · cited 2×
“In contrast, Nguyen et al. [16] discussed the use of federated distillation to decrease model complexity, using a private dataset called The Noisy Blind consisting of 1198 original images collected from four clinics.”
BackgroundMethodInfluentialFederatedScope: A Flexible Federated Learning Platform for Heterogeneity
Xie, Y., Wang, Z., Gao, D., Chen, D., Yao, L., Kuang, W., Li, Y., Ding, B., & Zhou, J. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3579075.3579081 · Cited by 84
Sharma, P. K., Park, J. H., & Cho, K. (2020) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102220 · Cited by 83 · cited 1×
“Additionally, Sharma et al. [211] discussed using DFL in the Internet of Battlefield Things (IoBT) as a defense system employing to strengthen the armed forces.”
Federated learning-based secure electronic health record sharing scheme in medical informatics
Salim, M. M., & Park, J. H. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3174823 · Cited by 80 · cited 1×
“Salim and Park [167] compared the results of their decentralized Convolutional Neural Network (CNN) model for Electronic Health Records (EHR) with a private Interplanetary File System (IPFS) and found promising results in accuracy, sensitivity, and specificity, similar to the traditional centralized…”
Non-IID data re-balancing at IoT edge with peer-to-peer federated learning for anomaly detection
Wang, H., Muñoz-González, L., Eklund, D., & Raza, S. (2021) · ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec) · doi:10.1145/3448300.3467827 · Cited by 77 · cited 2×
“Cybersecurity is also an important consideration in Industry 4.0, and several studies have investigated the use of DFL for anomaly and attack detection, such as the work published in [126].”
BackgroundInfluentialFully Decentralized Federated Learning-Based On-Board Mission for UAV Swarm System
Xiao, Y., Ye, Y., Huang, S., Li, H., Ma, Z., Xiao, M., Mumtaz, S., & Dobre, O. A. (2021) · IEEE Communications Letters · doi:10.1109/lcomm.2021.3095362 · Cited by 76 · cited 2×
“Despite the high communication cost and low flexibility, this topology is highly reliable and robust, as the network can still function when a few nodes or links fail [51].”
BackgroundMethodA Data Sharing Scheme Based on Federated Learning in IoV
Hu, X., Li, R., Wang, L., Ning, Y., & Ota, K. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3266100 · Cited by 76 · cited 1×
“Finally, Hu et al. [224] integrated Blockchain into a fully connected vehicle topology.”
BackgroundSystem Optimization of Federated Learning Networks With a Constrained Latency
Zhao, Z., Xia, J., Fan, L., Lei, X., Karagiannidis, G. K., & Nallanathan, A. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3128559 · Cited by 73 · cited 2×
“In this way, the network can extract information about the position, direction, and absolute velocity of each node [13].”
BackgroundAn Approach for Peer-to-Peer Federated Learning
Wink, T., & Nochta, Z. (2021) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w52860.2021.00034 · Cited by 72 · cited 1×
“The main drawback of DFL is that nodes cannot randomly choose d neighbors among existing nodes since there is no central coordinator to determine these associations [67].”
BackgroundEnhancing privacy preservation and trustworthiness for decentralized federated learning
Wang, L., Zhao, X., Lu, Z., Wang, L., & Zhang, S. (2023) · Information Sciences · doi:10.1016/j.ins.2023.01.130 · Cited by 72 · cited 1×
“Anonymization techniques, such as k -anonymity and l -diversity, use k and l values as performance metrics, ensuring privacy in DFL by making it difficult to re-identify models within a federation [96].”
MethodThroughput-Optimal Topology Design for Cross-Silo Federated LearningPreprint
Marfoq, O., Xu, C., Neglia, G., & Vidal, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12229 · Cited by 71
Abdel‐Basset, M., Moustafa, N., & Hawash, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3167663 · Cited by 71 · cited 1×
“Apart from ensuring the reliability of IIoT and the connectivity of industrial objects, Abdel-Basset et al. [185] proposed a Blockchain-orchestrated Edge Intelligence (BoEI) framework for cyberattack detection in IIoT.”
MethodCommunication-Efficient Design for Quantized Decentralized Federated Learning
Chen, L., Liu, W., Chen, Y., & Wang, W. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3363887 · Cited by 71 · cited 2×
“A recent contribution includes a method that applies the Lloyd-Max algorithm to DFL to minimize quantization distortion, with the resulting LMDFL algorithm able to adjust quantization levels adaptively [102].”
MethodAdvancements in Federated Learning: Models, Methods, and Privacy
Chen, H., Wang, H., Long, Q., Jin, D., & Li, Y. (2024) · ACM Computing Surveys · doi:10.1145/3664650 · Cited by 70 · cited 1×
“Additionally, Chen et al. [35] analyzed the advances in FL, including aspects such as communications, privacy, and security requirements in DFL.”
BackgroundAsynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
Liu, Q., Yang, B., Wang, Z., Zhu, D., Wang, X., Ma, K., & Guan, X. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3150182 · Cited by 70 · cited 1×
“In the energy and utilities sector, DFL supports predictive maintenance and demand forecasting, contributing to operational efficiency across companies [158].”
BackgroundOver-the-Air Decentralized Federated Learning
Shi, Y., Zhou, Y., & Shi, Y. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9517780 · Cited by 67
Blockchain-Enabled Federated Learning for UAV Edge Computing Network: Issues and Solutions
Zhu, C., Xiao, Z., Ren, J., & Qin, T. (2022) · IEEE Access · doi:10.1109/access.2022.3174865 · Cited by 67 · cited 1×
“Furthermore, Zhu et al. [213] used the same technology among multiple untrusted parties with anonymous, immutable, and distributed characteristics, achieving similar results in performance for UAV intelligent edge computing networks to the previous study.”
ResultFadl Federated-autonomous deep learning for distributed electronic health record
Liu, D., Miller, T., Sayeed, R., & Mandl, K. D. (2018) · arXiv · doi:10.48550/arxiv.1811.11400 · Cited by 65 · cited 1×
“The first study to present the privacy issues of server use in healthcare is [160].”
BackgroundDeep Federated Learning for IoT-based Decentralized Healthcare Systems
Elayan, H., Aloqaily, M., & Guizani, M. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498820 · Cited by 65 · cited 1×
“Similarly, Elayan et al. [163] proposed Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
BackgroundBillah, M., Mehedi, S. T., Anwar, A., Rahman, Z., & Islam, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.05192 · Cited by 64 · cited 2×
“Similarly, other authors explored the applicability of DFL in particular scenarios such as IoV [31], wireless communications [32], or UAV devices [33].”
BackgroundDecentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications
Al-Abiad, M. S., Obeed, M., Hossain, M. J., & Chaaban, A. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3253718 · Cited by 64 · cited 4×
“decentralized aggregation, thereby reducing overall energy consumption and latency while maintaining convergence rates [58].”
BackgroundInfluentialDistributed statistical estimation and rates of convergence in normal approximation
Minsker, S. (2019) · Electronic Journal of Statistics · doi:10.1214/19-ejs1647 · Cited by 62
Shiri, I., Sadr, A. V., Amini, M., Salimi, Y., Sanaat, A., Akhavanallaf, A., Razeghi, B., Ferdowsi, S., Saberi, A., Arabi, H., et al. (2022) · Clinical Nuclear Medicine · doi:10.1097/rlu.0000000000004194 · Cited by 61 · cited 1×
“For example, it is applied in different hospitals by training a federated model for tumor classification while keeping their Positron Emission Tomography (PET) images locally [116].”
MethodProactive Content Caching for Internet-of-Vehicles based on Peer-to-Peer Federated Learning
Yu, Z., Hu, J. W., Min, G., Xu, H., & Mills, J. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00083 · Cited by 60
Eclipse: Preserving Differential Location Privacy Against Long-Term Observation Attacks
Niu, B., Chen, Y., Wang, Z., Li, F., Wang, B., & Li, H. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3000730 · Cited by 58 · cited 1×
“The attackers could gain complete control of all traffic to the victim if all node connections belong to them [79].”
BackgroundDetecting model misconducts in decentralized healthcare federated learning
Kuo, T.-T., & Pham, A. (2021) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2021.104658 · Cited by 56 · cited 2×
“In other cases, it is preferable to rely on anomaly detection mechanisms [126] or model misbehavior detection [90] to detect malicious actors that may deteriorate DFL performance.”
BackgroundMethodDecentralised federated learning with adaptive partial gradient aggregation
Jiang, J., & Hu, L. (2020) · CAAI Transactions on Intelligence Technology · doi:10.1049/trit.2020.0082 · Cited by 56 · cited 1×
“At the same time, it reduces the convergence rate by adapting the step size of the stable gradient descent direction [97].”
BackgroundFabricFL: Blockchain-in-the-Loop Federated Learning for Trusted Decentralized Systems
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Dehghantanha, A., & Choo, K. R. (2021) · IEEE Systems Journal · doi:10.1109/jsyst.2021.3124513 · Cited by 51 · cited 3×
“Therefore, it is necessary to determine the confi-dence of the participants and the federated models to ensure trustworthiness, where robust privacy and security measures significantly contribute to this [92], [93].”
BackgroundMethodD-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning
Bellet, A., Kermarrec, A.-M., & Lavoie, E. (2022) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds55811.2022.00011 · Cited by 50 · cited 1×
“Depending on how the model aggregation is distributed across the network, some DFL topologies may face increased communication overhead [9].”
BackgroundAsynchronous Decentralized SGD with Quantized and Local UpdatesPreprint
Nadiradze, G., Sabour, A., Davies, P. M., Li, S., & Alistarh, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12308 · Cited by 50 · cited 1×
“This technique is effective in heterogeneous node data distributions and random topologies [88].”
MethodPersonalized Decentralized Federated Learning with Knowledge Distillation
Jeong, E., & Kountouris, M. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279714 · Cited by 50
Blockchain-Based Decentralized Model Aggregation for Cross-Silo Federated Learning in Industry 4.0
Ranathunga, T., McGibney, A., Rea, S., & Bharti, S. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3218704 · Cited by 48 · cited 1×
“Ranathunga et al. [189] introduced a similar cross-silo architecture using a network of aggregators to optimize model quality, minimize convergence time, and improve system performance in various industrial applications.”
BackgroundBACombo—Bandwidth-Aware Decentralized Federated Learning
Jiang, J., Hu, L., Hu, C., Liu, J., & Wang, Z. (2020) · Electronics · doi:10.3390/electronics9030440 · Cited by 47 · cited 4×
“• Strategies to select nodes and optimize the efficiency in gossip-based communication [72]–[75] Security and Privacy Malware Attacks • Determine the impacts of malware threats in decentralized scenarios [76]–[79]”
BackgroundMethodInfluentialμDFL: A Secure Microchained Decentralized Federated Learning Fabric Atop IoT Networks
Xu, R., & Chen, Y. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3179892 · Cited by 47
Decentralized and Lightweight Approach to Detect Eclipse Attacks on Proof of Work Blockchains
Alangot, B., Reijsbergen, D., Venugopalan, S., Szałachowski, P., & Yeo, K. S. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3069502 · Cited by 46 · cited 1×
“One of these threats is Eclipse attacks, which enable attackers to gain partial or full control of a participant by manipulating its connections with neighboring nodes [78].”
BackgroundQuantized Consensus by the ADMM: Probabilistic Versus Deterministic Quantizers
Zhu, S., & Chen, B. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2015.2504341 · Cited by 45 · cited 1×
“For example, Quantized Sparse SGD (QSGD) [109] and quantized ADMM [137] were proposed to reduce network overhead when exchanging model parameters.”
MethodSurvey on Federated-Learning Approaches in Distributed Environment
Gupta, R., & Alam, T. (2022) · Wireless Personal Communications · doi:10.1007/s11277-022-09624-y · Cited by 45
Wang, Z., Hu, Y., Yan, S., Wang, Z., Hou, R., & Wu, C. (2022) · Electronics · doi:10.3390/electronics11101548 · Cited by 45 · cited 3×
“[94] 2022 Detect brain tumor segmentation, using representative clinical datasets Cross-device Centralized Decentralized Real U-Net CFA FedPer Synchronous Asynchronous Random BRATS [149] Private [89] 2022 Detect misconduct model on specific sites from any learning iteration Cross-device Centralized Decentralized Simul…”
BackgroundMethodBreaking the centralized barrier for cross-device federated learning
Karimireddy, S. P., Jaggi, M., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2021) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 44
Trusted Decentralized Federated Learning
Gholami, A., Torkzaban, N., & Baras, J. S. (2022) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49033.2022.9700624 · Cited by 44 · cited 1×
“Therefore, it is necessary to determine the confi-dence of the participants and the federated models to ensure trustworthiness, where robust privacy and security measures significantly contribute to this [92], [93].”
BackgroundConfederated Learning: Federated Learning With Decentralized Edge Servers
Wang, B., Fang, J., Li, H., Yuan, X., & Ling, Q. H. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3241768 · Cited by 44 · cited 1×
“Finally, mechanisms to optimize KPIs are also essential to ensure the efficiency and multi-scenario adaptability of the approach [14].”
BackgroundPEPPER: Empowering User-Centric Recommender Systems over Gossip Learning
Belal, Y., Bellet, A., Mokhtar, S. B., & Nitu, V. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550302 · Cited by 43
Semi-Decentralized Federated Learning with Collaborative Relaying
Yemini, M., Saha, R., Özfatura, E., Gündüz, D., & Goldsmith, A. J. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834707 · Cited by 41
CE-Fed: Communication efficient multi-party computation enabled federated learning
Kanagavelu, R., Wei, Q., Li, Z., Zhang, H., Samsudin, J., Yang, Y., Goh, R. S. M., & Wang, S. (2022) · Array · doi:10.1016/j.array.2022.100207 · Cited by 40 · cited 4×
“• Federation from different types of devices, such as mobile phones or IoT devices [2], [42], [43] Participant Role • Identify the functionality of participants during federation [44], [45] Decentralization Schema • Techniques for enabling DFL while maintaining model convergence and data privacy [6], [46], [47]”
BackgroundMethodInfluentialQu, Y., Xu, C., Gao, L., Xiang, Y., & Yu, S. (2022) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2100173 · Cited by 39
Federated Learning for Maritime Environments: Use Cases, Experimental Results, and Open Issues
Giannopoulos, A., Gkonis, P. K., Bithas, P. S., Νομικός, Ν., Kalafatelis, A., & Trakadas, P. T. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12061034 · Cited by 39
Peer-to-Peer Variational Federated Learning Over Arbitrary Graphs
Wang, X., Lalitha, A., Javidi, T., & Koushanfar, F. (2022) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2022.3189051 · Cited by 37 · cited 1×
“However, each node can determine neighbors if global information is given when the topology is created, and neighbor discovery mechanisms are implemented during federation [64].”
BackgroundWhen Decentralized Optimization Meets Federated Learning
Gao, H., Thai, M. T., & Wu, J. (2023) · IEEE Network · doi:10.1109/mnet.132.2200530 · Cited by 35 · cited 1×
“One option presented in the literature is to continue aggregating them at a higher level [117], while another option is to accept the presence of different federated models based on the network topology and characteristics of the nodes [118].”
BackgroundDecentralized Federated Learning for Internet of Things Anomaly Detection
Lian, Z., & Su, C. (2022) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3488932.3527285 · Cited by 35 · cited 1×
“Another study, conducted by Lian and Su [183], discussed a similar approach with the IoT23 dataset [184], obtaining a model convergence 30% faster than in the previous study with an increase of only 3% in the overhead of the participants.”
ResultDeceFL: a principled fully decentralized federated learning framework
Yuan, Y., Liu, J., Jin, D., Yue, Z., Yang, T., Chen, R., Wang, M., Xu, L., Hua, F., Guo, Y., et al. (2022) · National Science Open · doi:10.1360/nso/20220043 · Cited by 34 · cited 1×
“It demonstrates its applicability to a wide range of real-world medical and industrial applications [135].”
BackgroundHADFL: Heterogeneity-aware Decentralized Federated Learning Framework
Cao, J., Lian, Z., Liu, W., Zhu, Z., & Ji, C. (2021) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18074.2021.9586101 · Cited by 34 · cited 2×
“• Update participants models independently at different times [58], [59] Peer-to-Peer Communications • Methods for designing P2P topologies in DFL [60]–[63]”
BackgroundEfficient and Reliable Overlay Networks for Decentralized Federated Learning
Hua, Y., Miller, K., Bertozzi, A. L., Qian, C., & Wang, B. (2022) · SIAM Journal on Applied Mathematics · doi:10.1137/21m1465081 · Cited by 32
Verhaelen, B., Mayer, F., Peukert, S., & Lanza, G. (2021) · Production Engineering · doi:10.1007/s11740-021-01041-7 · Cited by 31 · cited 1×
“It is essential to know these metrics to detect and resolve federation, communications, or security issues more quickly, reducing the frequency and duration of incidents while increasing efficiency [86].”
BackgroundExpander graph and communication-efficient decentralized optimization
Chow, Y. T., Shi, W., Wu, T., & Yin, W. (2016) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2016.7869675 · Cited by 30 · cited 2×
“• Measure of robustness, flexibility, fault tolerance, cost, or security [11] Partially Connected Networks • Define the classification in star, ring or random structured networks [52], [53]”
BackgroundWireless Ad Hoc Federated Learning: A Fully Distributed Cooperative Machine LearningPreprint
Ochiai, H., Sun, Y., Jin, Q., Wongwiwatchai, N., & Esaki, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.11779 · Cited by 30 · cited 1×
“Similarly, Ochiai et al. [188] proposed a similar approach for ad-hoc wireless environments, achieving an average accuracy of 95% for the test IID dataset compared to on-device training, which obtained 84.7%.”
InfluentialQuantized Distributed Federated Learning for Industrial Internet of Things
Ma, T., Wang, H., & Li, C. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3139772 · Cited by 27 · cited 1×
“Ma et al. [52] defined Q-DFL for a quantized selection of network nodes.”
BackgroundSAFECAR: A Brain–Computer Interface and intelligent framework to detect drivers’ distractions
Beltrán, E. T. M., Pérez, M. Q., Bernal, S. L., Pérez, G. M., & Celdrán, A. H. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117402 · Cited by 27 · cited 1×
“developing automated solutions to detect distractions while driving and to alert vehicles on the road intelligently [213].”
BackgroundSelf-citationDecentralized Federated Learning Over Slotted ALOHA Wireless Mesh Networking
Salama, A., Stergioulis, A., Hayajneh, A. M., Zaidi, S. A. R., McLernon, D., & Robertson, I. D. (2023) · IEEE Access · doi:10.1109/access.2023.3246924 · Cited by 26 · cited 1×
“Finally, it is worth mentioning that other studies have explored the use of innovative techniques in DFL, such as P2P with knowledge distillation, for various applications such as social network scenarios or IoT device identification [201], [204], [206].”
BackgroundJointly Learning from Decentralized (Federated) and Centralized Data to Mitigate Distribution ShiftPreprint
Augenstein, S., Hard, A., Partridge, K., & Mathews, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12150 · Cited by 26 · cited 2×
“This central node aggregates the model parameters shared periodically by each trainer and creates a robust central model distributed among the nodes [6].”
BackgroundDACFL: Dynamic Average Consensus-Based Federated Learning in Decentralized Sensors Network
Chen, Z., Li, D., Zhu, J., & Zhang, S. (2022) · Sensors · doi:10.3390/s22093317 · Cited by 26 · cited 1×
“transforms the aggregation of the DFL model into a local training procedure as a discrete time series, whose convergence guarantees convex objectives [128].”
MethodA Layer Selection Optimizer for Communication-Efficient Decentralized Federated Deep Learning
Barbieri, L., Savazzi, S., & Nicoli, M. (2023) · IEEE Access · doi:10.1109/access.2023.3251571 · Cited by 25 · cited 2×
“aim to optimize the balance between improving the quality of the model and saving communication resources, which can result in a more sustainable federation policy [100].”
BackgroundMethodDecentralized Event-Triggered Federated Learning with Heterogeneous Communication Thresholds
Zehtabi, S., Hosseinalipour, S., & Brinton, C. G. (2022) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc51059.2022.9993258 · Cited by 25 · cited 2×
“However, they cause higher communication costs and lower generalization due to staleness [60].”
BackgroundTORR: A Lightweight Blockchain for Decentralized Federated Learning
Ma, X., & Xu, D. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3288078 · Cited by 24 · cited 1×
“This approach optimizes performance by mitigating slower device impacts and maximizing storage utilization [127].”
BackgroundDecentralized Consensus Optimization Based on Parallel Random Walk
Ye, Y., Chen, H., Ma, Z., & Xiao, M. (2019) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2955442 · Cited by 23 · cited 2×
“To address this limitation, additional processes are presented to determine the location of a node using random walks [123] and node selection techniques, relying on the heuristics of the distance between nodes or underlying device features [72].”
MethodToward Scalable and Robust AIoT via Decentralized Federated Learning
Pinyoanuntapong, P., Huff, W. H., Lee, M., Chen, C., & Wang, P. (2022) · IEEE Internet of Things Magazine · doi:10.1109/iotm.006.2100216 · Cited by 23 · cited 2×
“Nevertheless, asynchronous communications are well suited for cross-device DFL scenarios, in which nodes have varying computational capability and intermittent availability [59].”
BackgroundBeyond Spectral Gap: The Role of the Topology in Decentralized Learning
Vogels, T., Hendrikx, H., & Jaggi, M. (2022) · neural information processing systems · doi:10.52202/068431-1094 · Cited by 23
Walk Proximal Gradient: An Energy-Efficient Algorithm for Consensus Optimization
Mao, X., Gu, Y., & Yin, W. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2875057 · Cited by 22 · cited 1×
“These include Random Walk ADMM (WADMM) [134], Parallel Random Walk ADMM (PW-ADMM) [123] and Walk Proximal Gradient (WPG) [135] which are commonly used in increment-based approaches.”
MethodDecentralized Online Federated G-Network Learning for Lightweight Intrusion Detection
Nakıp, M., Gül, B. C., & Erol Gelenbe, A. (2023) · Proceedings - International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems · doi:10.1109/mascots59514.2023.10387644 · Cited by 22 · cited 1×
“Finally, the telecommunications sector benefits from DFL in optimizing network performance and anomaly detection, allowing network providers to share insights without compromising proprietary information [159].”
BackgroundMitigating communications threats in decentralized federated learning through moving target defense
Beltrán, E. T. M., Sánchez, P. M. S., Bernal, S. L., Bovet, G., Pérez, M. G., Pérez, G. M., & Celdrán, A. H. (2024) · Wireless Networks · doi:10.1007/s11276-024-03667-8 · Cited by 21 · cited 2×
“Specifically, random neighbor selection and dynamic IP/port switching offer enhanced resilience against communication-based threats [83].”
BackgroundSelf-citationA Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices
Chen, Z., Liao, W., Pu, T., Wang, Q., & Yu, W. (2022) · Future Internet · doi:10.3390/fi14050138 · Cited by 20 · cited 2×
“However, unlike traditional P2P networks, DFL deals with a dynamic and heterogeneous topology, where participants often change their location or role in the federation [62].”
BackgroundFLoBC: A Decentralized Blockchain-Based Federated Learning Framework
Ghanem, M. C., Dawoud, F., Gamal, H., Soliman, E., ElBatt, T., & Sharara, H. (2022) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca55292.2022.9922258 · Cited by 20
Assessing Anonymous and Selfish Free-rider Attacks in Federated Learning
Wang, J., Chang, X., Rodríguez, R. J., & Wang, Y. (2022) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc55528.2022.9912903 · Cited by 18 · cited 1×
“Free Rider attacks are also a type of attack that takes advantage of DFL without contributing useful data to it during the training process [125].”
BackgroundStatistical Evaluation of Diagnostic Performance
Zou, K. H., Liu, A., Bandos, A. I., Lucila Ohno-machado, A., & Rockette, H. E. (2011) · Chapman & Hall/CRC eBooks · doi:10.1201/b11031 · Cited by 17
Towards a Peer-to-Peer Federated Machine Learning Environment for Continuous Authentication
Monschein, D., Peregrina, J. A., Piotrowski, T., Nochta, Z., Waldhorst, O. P., & Zirpins, C. (2021) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc53001.2021.9631491 · Cited by 17 · cited 1×
“Additionally, Monschein et al. [190] addressed the challenge of acquiring large amounts of data to train powerful ML models, which is often an overwhelming task for a single organization.”
BackgroundNetwork Gradient Descent Algorithm for Decentralized Federated Learning
Wu, S., Huang, D., & Wang, H. (2022) · Journal of Business and Economic Statistics · doi:10.1080/07350015.2022.2074426 · Cited by 17 · cited 1×
“In non-IID scenarios where adaptive training models can be challenging on resource-constrained devices, these models can be particularly useful [108].”
BackgroundLumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices
Pan, Q., Zhu, Y., & Chu, L. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00149 · Cited by 15 · cited 1×
“To improve the previous scenarios, Pan et al. [199] utilized a tree constructor to improve representation capability given the limited structural information and a Monte Carlo Markov Chain-based algorithm to mitigate workload imbalance caused by degree heterogeneity.”
Beyond spectral gap: The role of the topology in decentralized learningPreprint
Vogels, T., Hendrikx, H., & Jaggi, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.03093 · Cited by 14
Sánchez, P. M. S., Celdrán, A. H., Pérez, E. T. M., Demeter, D., Bovet, G., Pérez, G. M., & Stiller, B. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05510-1 · Cited by 14
Self-citationDecentralized Quantum Federated Learning for Metaverse: Analysis, Design and ImplementationPreprint
Gurung, D., Pokhrel, S. R., & Li, G. (2023) · arXiv.org · doi:10.48550/arxiv.2306.11297 · Cited by 13 · cited 1×
“Beyond the previously discussed scenarios, DFL is also relevant in emerging areas such as smart cities and metaverse, where it enhances urban planning and service provision, all while facilitating privacy-preserving data sharing between real and virtual entities [156].”
BackgroundBristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. EnvironmentsPreprint
Verbraeken, J., de Vos, M., & Pouwelse, J. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.11006 · Cited by 13 · cited 1×
“The attacker can command multiple pseudonyms to flood a targeted node with pairing requests, rendering it unable to respond to and communicate with legitimate nodes [80].”
BackgroundA Reputation-Based Resilient and Recoverable P2P Botnet
Yin, J., Cui, X., & Li, K. (2017) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc.2017.20 · Cited by 12 · cited 1×
“However, the information obtained may have been modified during the exchange, adding malicious data using rootkits or including the participant in a botnet [75], [76].”
Schwab, A., & Lunze, J. (2021) · European Journal of Control · doi:10.1016/j.ejcon.2021.04.006 · Cited by 12 · cited 1×
“Other alternatives are to employ distributed Delaunay triangulation networks for wireless sensor networks or regular random topologies for data center and memory interconnection networks [122].”
MethodDecentralized federated meta‐learning framework for few‐shot multitask learning
Li, X., Li, Y., Wang, J., Chen, C., Yang, L., & Zheng, Z. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.22951 · Cited by 11 · cited 1×
“It uses information from the activities performed to better adapt to new tasks [112].”
ProxyFL: Decentralized Federated Learning through Proxy Model SharingPreprint
Kalra, S., Wen, J., Cresswell, J. C., Volkovs, M., & Tizhoosh, H. R. (2021) · Research Square · doi:10.21203/rs.3.rs-1168002/v1 · Cited by 10
On the Decentralization of Blockchain-enabled Asynchronous Federated Learning
Wilhelmi, F., Guerra, E., & Dini, P. (2023) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft57336.2023.10175411 · Cited by 9 · cited 1×
“Wilhelmi et al. [193] studied the impact of ledger inconsistencies on DFL performance.”
BackgroundA Hybrid Incentive Mechanism for Decentralized Federated Learning
Qi, M., Wang, Z., Chen, S., & Xiang, Y. (2022) · Distributed Ledger Technologies Research and Practice · doi:10.1145/3538226 · Cited by 8 · cited 2×
“DLT technologies, such as Blockchain, provide an ideal solution for this requirement by ensuring the immutability of exchanged models [68].”
Background
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
Decentralized Federated Learning: A Survey and Perspective
Yuan, L., Wang, Z., Sun, L., Yu, P. S., & Brinton, C. G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3407584 · Cited by 290
Chellapandi, V. P., Yuan, L., Brinton, C. G., Żak, S. H., & Wang, Z. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3332675 · Cited by 236
Abbas, S. R., Abbas, Z., Zahir, A., & Lee, S. W. (2024) · Healthcare · doi:10.3390/healthcare12242587 · Cited by 228
Distributed Foundation Models for Multi-Modal Learning in 6G Wireless Networks
Du, J., Lin, T., Jiang, C., Yang, Q., Bader, C. F., & Han, Z. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.009.2300501 · Cited by 187
“SL enhances privacy by transmitting only non-sensitive features, reduces bandwidth, and boosts efficiency by allocating lighter tasks to local devices and distributed paradigm, federated learning (FL) is well-suited for assisting the data parallelism [11].”
BackgroundA systematic review of federated learning: Challenges, aggregation methods, and development tools
Guendouzi, S. B., Ouchani, S., Assaad, H. E., & Zaher, M. E. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103714 · Cited by 199
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.