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 301–400 of 626
FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning
Mueller, B., Street, W. N., Baek, S., Lin, Q., Yang, H. J., & Huang, Y. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825304 · Cited by 2
“As the number of clients grows, the central server can also become a communication bottleneck due to bandwidth limitations, network congestion, and the complexity of synchronizing updates from clients with diverse hardware capabilities [6].”
BackgroundDFedCL: Decentralized Federated Collaborative Learning with Privacy Protection
Hu, J., Li, Y., Liu, L., & Lou, H. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831860 · Cited by 4
“R ELATED W ORK Decentralized Federated Learning (DFL): DFL has emerged as a fully decentralized paradigm that mitigates the vulnerabilities associated with single points of failure due to central server disruptions while simultaneously optimizing the allocation of communication resources [10].”
GLow - A Novel, Flower-Based Simulated Gossip Learning Strategy
Belenguer, A., Pascual, J. A., & Navaridas, J. (2026) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2026.105272 · Cited by 2
Zhou, Y., Cui, F., Che, J., Ni, M., Zhang, Z., & Li, J. (2025) · Electronics · doi:10.3390/electronics14040745 · Cited by 2
Mobility-aware Decentralized Federated Learning for Autonomous Underwater Vehicles
He, H., Du, J., Jiang, C., Wang, J., & Song, J. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901125 · Cited by 1
“Therefore, decentralized federated learning (DFL) [7], which leverages device-to-device (D2D) communication for collaborative training, has emerged as a preferred option.”
A self-organized MoE framework for distributed federated learning
Lee, J., & Kim, W. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.107798 · Cited by 2
Luo, S., Zhang, P., Song, X. G., Fan, P., Xing, H., Luo, L., & Yu, H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3552220 · Cited by 3
Towards a Lightweight Platform for Human-Robot Interaction in Federated Edge and IoT Environments
Zhang, S., Li, Z., Qin, X., & Xu, H. (2025) · International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems · doi:10.1145/3722570.3726881 · Cited by 2
Wang, T., Li, P., Feng, P., Wei, X., Qian, L., & Wu, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3569669 · Cited by 2
Trillos, N. G., Akash, A. K., Li, S., Riedl, K., & Zhu, Y. (2025) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2024.0235 · Cited by 13
“One popular FL paradigm is decentralized federated learning (DFL) [3–5, 34, 49 ].”
InfluentialLin, X. S., Zhao, X., Yin, Z., Pan, H., Jing, P., Li, W., Wang, K., & Shu, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07516-z · Cited by 3
P2P-Fed: A Decentralized Federated Learning Platform on Structured Peer-to-Peer Systems
Lim, A., Jang, S., & Lee, J. (2025) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid64434.2025.00013 · Cited by 7
Singh, B., Nayyar, A., & Kaunert, C. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-80949-1_5 · Cited by 5
Gupta, A., Ranjan, R., Gupta, B., Das, D., & Chakraborty, C. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3600989 · Cited by 2
“This approach reduces the amount of communication required while preserving the privacy of individual vehicles, as the raw data is never shared but only model updates are shared among the nodes [23].”
Abed, S. H., Sabar, N. R., & Mahmood, A. N. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103858 · Cited by 5
Energy Efficiency Optimization for Federated Learning in Cell-free Massive MIMO Systems
Dang, X.-T., & Shin, O. (2024) · International Conference on Communications and Electronics (ICCE) · doi:10.1109/icce62051.2024.10634733 · Cited by 2
“In FL, a central location known as the server oversees the training of a learning model across remote devices [4], [6], [7].”
BackgroundHuman-Centric Enterprise Security: Advancing Access Control through AI-Driven AdministrationPreprint
Mariam, A., & Berrada, A. (2024) · doi:10.22541/au.170708972.23906177/v1 · Cited by 5
Islam, N., & Zulkernine, M. (2025) · arXiv · doi:10.48550/arxiv.2503.01089 · Cited by 9
“Common data types in IoV and their privacy challenges are discussed in this ecosystem section.”
InfluentialYuan, H., Alghunaim, S. A., & Yuan, K. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10384058 · Cited by 1
“As a result, they have been widely applied across various domains, including deep training with massive GPUs [1]–[5] and edge computing with extensive embedded devices [6]–[8].”
BackgroundWu, C., Gupta, P., & Mohapatra, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13897-3.00007-2 · Cited by 2
Networked Federated Meta-Learning Over Extending Graphs
Cheema, M. A., Gogineni, V. C., Rossi, P. S., & Werner, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3443467 · Cited by 5
“We consider a distributed federated network of IoT devices [39] represented by an undirected graph at time t ,”
ECG Data Classification with Privacy Preservation in the IoT Context
Serban, C. M., Sebestyen, G., & Hângan, A. (2024) · IEEE Conference on Information Technology and Data Science (CITDS) · doi:10.1109/citds62610.2024.10791351 · Cited by 1
“As identified in [2], [3] and [4], the most common ones would be Industry 4.0, healthcare, smart homes, smart cities, and vehicles.”
InfluentialAI Folk: Sharing Machine Learning Models in a Multi-Agent Community
Olaru, A., Sorici, A., Nan, M., & Iancu, D.-T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-82073-1_12 · Cited by 1
Bibliometric Analysis: Research Trends of Privacy in Big Data and its Applications
Rauf, A., Tariq, U., Tang, H., & Shishir, M. A. (2024) · International Conference on Data Science and Information Technology (DSIT) · doi:10.1109/dsit61374.2024.10881578 · Cited by 2
Guo, N., Pan, Y., & Yang, Y. (2024) · International Conference on Communication and Network Security (ICCNS) · doi:10.1145/3711618.3711641 · Cited by 2
Decentralized Federated Learning with Auto-switchable Local Optimizers
Li, T., Chang, Z., Pan, Z., Yang, S., Xu, W., & Chen, Y. (2025) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip64458.2025.10898094 · Cited by 1
“Decentralized federated learning (DFL) has emerged as a promising paradigm in large-scale machine learning [1].”
A Decentralized Federated Learning Model Based on Global Channel Selection
Cheng, J., Cai, Y., Zhao, J., Yang, Y., Zhang, S., & Cao, Y. (2024) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic64248.2024.10912898 · Cited by 1
“The key to solving this problem is to design an efficient parameter transmission mechanism to reduce unnecessary communication while ensuring the effectiveness of model updates [3].”
Falafels: A Tool for Estimating Federated Learning Energy Consumption via Discrete Simulation
de Barochez, A. M. H., Plassart, S., & Monnet, S. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-87769-8_13 · Cited by 3
“[2] separates FL systems in three categories.”
Yan, Q., Wang, G., Zhu, D., & Li, J. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425520135 · Cited by 2
A Survey on Privacy-Preserving Federated Learning in Internet of Things (IoT)
Raghav, S., Krishna, B. V., & Vanipriya, C. (2025) · International Conference on Next Generation Communication & Information Processing (INCIP) · doi:10.1109/incip64058.2025.11019612 · Cited by 2
“The survey begins by delineating the foundational principles of federated learning and delving into the unique challenges posed by the decentralized and heterogeneous nature of IoT environments [4].”
Joint Aggregation Node Selection and Power Adjustment for Federated Learning in IoV
Sang, Z., Meng, C., Yan, W., Gao, B., Xiong, K., & Fan, P. (2025) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr65461.2025.11072661 · Cited by 1
“Nevertheless, a key challenge in DFL is how to efficiently aggregate LMs without a fixed central server [5].”
Pan, Q., & Nakao, A. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3589368 · Cited by 1
“Federated learning (FL) is a promising paradigm to solve this issue, where multiple servers in different areas collaborate to train the global high-quality AI model [26], [27], [28].”
De-VertiFL: A Solution for Decentralized Vertical Federated Learning
Celdrán, A. H., Feng, C., Banik, S., Bovet, G., Pérez, G. M., & Stiller, B. (2025) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms57970.2025.11073609 · Cited by 2
“Additionally, while some research has explored decentralized implementations of HFL, the majority focuses on centralized approaches [4].”
Self-citationZhang, C., Lian, Z., Wang, W., Huang, H., & Su, C. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108014 · Cited by 1
Incentive Mechanisms for Federated Learning in Multi-Cloud Environments
Singh, T., Shreshth, V., Raj, A., Swain, S., Bandyopadhyay, A., & Sharma, N. (2025) · International Conference on Computational Intelligence and Communication Technologies (CCICT) · doi:10.1109/ccict65753.2025.00054 · Cited by 1
Privacy-Preserving Collaborative Intelligence for IoT Cybersecurity: A Federated Learning Approach
Abraham, F., & Ofoe, N. T. (2025) · International Journal of Scientific Research and Modern Technology. · doi:10.38124/ijsrmt.v4i9.791 · Cited by 1
Federated learning-enabled CNT sensor networks for VOC detection and environmental monitoring
Shafiq, M., Chitta, S., Kaviarasi, J., Sabeenian, R. S., Rao, P. V. V., & Umamahesh, G. (2025) · Microchemical Journal · doi:10.1016/j.microc.2025.115412 · Cited by 1
Li, L., Guo, C., Tang, X., & Liu, Y. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111732 · Cited by 3
Cui, M., Cheng, H., Guo, X., Xiang, H., Yi, K., Li, X., & Xu, X. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00027 · Cited by 1
“By keeping data localized and sharing only model updates, federated learning inherently enhances service security [7] and mitigates privacy risks [8]–[10].”
FedDSSL: Decentralized Federated Semi-Supervised Learning for Limitedly Annotated Data
Huang, Y., Zhang, B., Kong, L., Li, Q., & Cui, L. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00115 · Cited by 1
“Decentralized federated learning [4] has further broken through the traditional federated learning’s dependence on a single central server by enabling direct communication and model update transmission between clients.”
Raju, V. V. R., Ranaveer, I., Alabdeli, H. M., Selvaprasanth, P., Raghatate, K. S., & Leoni Sharmila, S. (2025) · International Conference on Metaverse and Current Trends in Computing (ICMCTC) · doi:10.1109/icmctc62214.2025.11196500 · Cited by 1
“The biggest advantage of federated learning (FL) is that it allows training AI models on decentralized datasets without data sharing while addressing customers’ concerns about data security and compliance [9].”
Enhancing Federated Learning in Edge Computing With Secure Aggregation and Dynamic Verification
Li, M., Tian, Y., Zhang, J., Xiong, J., Cui, X., & Ma, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3625654 · Cited by 1
“Federated learning (FL) [1], [2] is characterized by the training of models through transmitting model parameters without exchanging the dataset, providing a new approach to data protection in edge computing.”
Architectural patterns for blockchain-enabled federated learning: A systematic literature review
Wang, J., Shi, D., Li, S., Yan, J., Wang, Y., Mao, Q., Liu, Y., Zhu, L., & Zhang, H. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112695 · Cited by 2
Integrating Identity-Based Identification Against Adaptive Adversaries in Federated Learning
Szelag, J. K., Chin, J., Ansell, L., & Yip, S.-C. (2025) · IEEE Access · doi:10.1109/access.2025.3609448 · Cited by 2
“The FL architecture may vary depending on the needs of the system and heterogeneity of data that the clients own [38], [39].”
Lian, M., Zhao, Y., Zhang, Q., Musumeci, F., Tornatore, M., & Zhang, J. (2025) · European Conference on Optical Communication · doi:10.1109/ecoc66593.2025.11263140 · Cited by 1
Federated clustering: An unsupervised cluster-wise training for decentralized data distributions
Nardi, M., Valerio, L., & Passarella, A. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108294 · Cited by 3
“Typically, this process is coordinated by a central server, but serverless protocols have also been proposed [4].”
Tummala, V. M. R., Kakarla, J. H. H., Hazra, A., & Menon, V. G. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3643908 · Cited by 1
“FedCSL uses a ring topology [24], where hospitals sequentially receive, train, and forward the model.”
Identification of Solar Panel Conditions Using Fully Decentralized Federated Learning
Kazemi, K. (2025) · International Conference on Control, Instrumentation, and Automation · doi:10.1109/iccia69223.2025.11286106 · Cited by 1
“This peer-to-peer paradigm enhances resilience, eliminates central bottlenecks, and allows knowledge to diffuse gradually across the network [15].”
Adaptive model splitting with sample-efficient reinforcement learning for federated learning
Zhang, N. N., Zeng, K., Wen, H., & Shen, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130875 · Cited by 1
Sakho, T. M., & Ben‐Othman, J. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161744 · Cited by 3
“In DFL topologies, the two main communication schemes are peer-to-peer and gossip learning [22].”
Analysis of Dynamic ADR Algorithms for LoRa Networks in IoT Environments
Zhang, H., Yang, M., Hu, S., Yu, H., Han, X., & Wang, J. (2025) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2025.3621637 · Cited by 1
Chen, Y.-Y. (2025) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2025.105583 · Cited by 1
A Unified Convergence Analysis of Decentralized Federated Learning at the Edge
Jiang, C., Fan, J., Halabi, T., & Haque, I. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3648579 · Cited by 1
“To overcome these, DFL facilitates direct collaboration among devices, eliminating the need for a central coordination server and enhancing robustness, trust, and resource distributions [3], [4].”
InfluentialLei, X., Fang, S., & Su, X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3648731 · Cited by 2
“In comparison to the centralized counterpart, the decentralized FL leverages a fully distributed network architecture (e.g., D2D, mesh, or sponta-neous), which is more scalable and robust [28], [29], [30], [31], [32].”
Fault Tolerant and Intelligent Reliability Assurance in Cloud-Edge Systems
Xiong, Z., Meng, S., Yao, S., & Luo, L. (2025) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa66321.2025.00028 · Cited by 1
Malik, A., & Qaisar, S. M. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3652563 · Cited by 1
“In this context, Federated Learning (FL) has recently provided a promising paradigm, enabling collaborative training over distributed clients without sharing raw data [8].”
Gao, Y. (2025) · IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · doi:10.1109/auteee67053.2025.11322177 · Cited by 1
“The convolutional layer automatically extracts local features by sliding convolutional kernels, effectively capturing the abnormal patterns of different intrusion behaviors in the feature space [13].”
Building Energy Consumption Prediction Based on Clustering and Privacy Preserving Federated Learning
Jian, H., Leng, J., Li, L., & Zhou, X. (2025) · IEEE International Conference on Smart Power and Energy Technologies (SPET) · doi:10.1109/spet67577.2025.11335423 · Cited by 1
Zhang, C., Lyu, X., Liang, Z., Ren, C., Hou, Y., & Cui, Q. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3656282 · Cited by 4
“Synchronization topology design significantly impacts the training e ffi ciency and scalability of DFL [34], [35], [36].”
Ramírez-Gordillo, T., Pujol, F. A., & Mora, H. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132828 · Cited by 2
Robust Stochastic Power Allocation for Industrial IoT Federated Learning with Neurosymbolic AI
Goswami, P., Iqbal, A., & Choi, K. (2026) · Mathematics · doi:10.3390/math14030547 · Cited by 4
SmartFLow: A Communication-Efficient SDN Framework for Cross-Silo Federated Learning
Hamdan, O. A., Che, H., Arslan, E., & Arifuzzaman, M. (2026) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc65079.2026.11366422 · Cited by 3
“In synchronous federated learning, the server must wait for all clients to finish uploading before proceeding to the next round [20].”
Srivastava, M., Kumar, G., & Singh, R. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111022 · Cited by 1
Beyond Centralized AI: Blockchain-Enabled Decentralized Learning
Wang, D., Ma, T., Zhu, J., & Duan, H. (2026) · Future Internet · doi:10.3390/fi18020098 · Cited by 1
“Current studies mitigate this overhead by restricting on-chain storage to lightweight information (such as verification proofs or participant identification) while keeping heavy data (e.g., full model parameters) off-chain and local [7,8].”
A Weighted Asynchronous Federated Learning Scheme to Combat Model Poisoning Attacks
Wang, J., Tang, Y., Cheng, H., & Song, J. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387697 · Cited by 1
“Even with the aforementioned advantages, traditional federated learning suffers from severe problems such as low communication efficiency and low resource utilization in synchronous federated learning [4].”
Federated learning for secure and private data analysis in decentralized networks
Pradeepa, K., Sottarov, A., Deogaonkar, A., Avasthi, V., Rakhimov, R. R., & Singhal, A. (2025) · Modern Electronics Devices and Intelligent Communication Systems (MEDCOM) · doi:10.1109/medcom67532.2025.11405000 · Cited by 1
Hao, Z., He, Q., Chang, C., Xu, Z., Li, H., Guo, J., & Du, J. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411283 · Cited by 1
Topology-Optimal Multiple Gossip Steps for Decentralized Federated Learning via Gossip Tensor
Zhong, Y., Ma, L., & Yan, X. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3670013 · Cited by 1
“A systemic review of existing DFL studies can be found in [38].”
Cui, Z., Zhang, X., & Zhou, S. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132034 · Cited by 1
Beltrán, E. T. M., Gash, E., Bovet, G., Celdrán, A. H., & Stiller, B. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112225 · Cited by 1
Self-citationXu, F., Wei, X., Zhao, Z., & Sun, P. (2026) · Scientific Reports · doi:10.1038/s41598-026-44843-4 · Cited by 1
Communication-Efficient Multi-Level Decentralized Federated Learning for Trajectory Prediction
Benhelal, M. S., Jouaber, B., Afifi, H., & Moungla, H. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432481 · Cited by 2
“Also, this architecture is prone to increased latency due to bottlenecks [14].”
Federated Learning at the Edge: Enabling AI in 5G/6G Networks and Massive IoT
Ioannou, I. I., Christophorou, C., & Vassiliou, V. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1014595 · Cited by 1
Decentralized Federated Learning for Internet of Vehicles With Asymmetric Networks
Ji, Q., Wen, G., & Fang, X. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3677043 · Cited by 1
Pacioni, E., Muller, C., de Vega, F. F., & Calvaresi, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23607-4_31 · Cited by 1
Ma, X., Yang, L., Wang, H., & Chen, L. (2026) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-026-00901-w · Cited by 4
Du, J., Qin, N., Huang, D., Jia, X., & Zhang, Y. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3690858 · Cited by 1
Federated training of spiking neural networks on edge hardware for audio processing
Kaimal, S. S., Ashwin, J. B., Reka, S. S., & Venugopal, P. (2026) · Frontiers in Neuroscience · doi:10.3389/fnins.2026.1827009 · Cited by 1
Jiang, L., Ming, X., Leng, J., Xu, J., Sha, W., & Zhang, X. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104866 · Cited by 2
Data Heterogeneity and Byzantine Resiliency in Decentralized Federated Learning
Ajibuwa, O., Odeyomi, O. T., Yuan, X., Roy, K., & Rawat, D. B. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3704583 · Cited by 1
Generative AI with federated learning
Yao, Z., Yang, D., & Wang, Y. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-341497-8.00022-5 · Cited by 2
Peer-to-Peer Federated Learning: A Comprehensive Survey
Allen, A., Mylonas, A., Vidalis, S., & Pitropakis, N. (2026) · AI · doi:10.3390/ai7070243 · Cited by 2
A Dual-Level Selective Unlearning Framework for Multi-Agent Decentralized Federated Learning
Xie, Z.-Q., Lin, Y.-J., Gao, Z.-P., & Fan, J. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3711105 · Cited by 2
Genetic Programming in Federated Aggregation: A Comparison of FedGP with State of the Art Methods
Pacioni, E., Muller, C., de Vega, F. F., & Calvaresi, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-25035-3_26 · Cited by 1
Guenzburger, E., & Hummel, P. (2026) · The American Journal of Bioethics · doi:10.1080/15265161.2026.2690958 · Cited by 1
Kuo, K., Yadav, C., & Smith, V. (2026) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml68715.2026.00020 · Cited by 1
DRL-Based Cost-Driven Adaptive Logic Tree Generation for Serverless Federated Learning Aggregation
Yan, H., Li, X., Pan, L., & Liu, S. (2026) · Big Data Mining and Analytics · doi:10.26599/bdma.2025.9020103 · Cited by 1
Convergence Visualizer of Decentralized Federated Distillation with Reduced Communication Costs
Taya, A., Nishiyama, Y., & Sezaki, K. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437801 · Cited by 1
“Hence, DFL has been developed to address this limitation [4], [5], [8], [9].”
BackgroundAn Edge Computing Framework for Data Analysis in Intelligent Transportation Systems
Sharma, S., & Bali, R. S. (2024) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon60754.2024.10511983 · Cited by 1
“[19], [20] The updated pseudo global model is compared with the existing pseudo global model and if there is an update more than the defined the threshold, then the newer pseudo global model is shared over the backbone network to the tier 4.”
MethodWang, C., Pan, C., Gan, Q., Liu, Z., Liu, N., & Zhang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5101-3_10 · Cited by 2
Federated Learning for Collaborative Cyber Defense
Muzammal, S. M., Bibi, R., Waseem, H., Din, S. N. U., Jhanjhi, N. Z., & Tayyab, M. A. (2024) · Advances in digital crime, forensics, and cyber terrorism book series · doi:10.4018/979-8-3693-8944-7.ch001 · Cited by 2
SiFT: A Serial Framework with Textual Guidance for Federated Learning
Li, X., Zhang, W., Yu, Y., Zheng, W., Zhang, T., & Wang, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72117-5_61 · Cited by 5
Gayathri, S., & Surendran, D. (2024) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic61668.2024.10730996 · Cited by 2
“…notably federated learning and cloud integration, as catalysts for bolstering anomaly detection capabilities within WSN. Federated learning, a decentralized machine learning paradigm, facilitates collaborative model training across distributed sensor nodes while safeguarding data privacy [6].”
BackgroundDFedMD: Decentralized Federated Learning using Model Distillation
Abiru, S., & Tamura, K. (2024) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scisisis61014.2024.10759998 · Cited by 1
“To address these problems, decentralized FL (DFL) [7]–[9], which does not deploy servers, has been studied.”
SAFARI: Self-regulAted Clustered FederAted Learning in a HeteRogeneous EnvIronment
Puppala, S., Hossain, I., Alam, M. J., & Talukder, S. K. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00059 · Cited by 1
“Despite its benefits, FL faces challenges such as communication inefficiencies and reliance on centralized systems, which can lead to increased latency and costs [1], [2], [3].”
FL-EGM: Decentralized Federated Learning using Aggregator Selection with Enhanced Global Model
Khan, M. K. U., Zhang, K., & Talhi, C. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00067 · Cited by 3
Trust Mechanisms in Decentralized Federated Learning: Enhancing Model Parameter Aggregation
Fan, X., Chu, J., Li, Z., Hu, J., & Li, T. (2024) · International Conference on Industrial Automation, Robotics and Control Engineering (IARCE) · doi:10.1109/iarce64300.2024.00062 · Cited by 1
“In scenarios with data heterogeneity, decentralized federated learning often performs worse than centralized federated learning [38-39].”
Federated Learning for Secure and Privacy-Preserving Medical Diagnostics
Gupta, G., Kant, R., & Adem, A. M. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-2827-0.ch006 · Cited by 3
Panwar, A., Gaba, P., Sugandh, U., & Bohra, N. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9789815322224125030006 · Cited by 1
Biswas, S., Kermarrec, A.-M., Sharma, R. K., Trinca, T., & de Vos, M. (2025) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml64287.2025.00045 · Cited by 1
“This assumption aligns with the notion that DL is often employed in enterprise contexts, where network access is typically restricted [29].”
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.