Federated Learning for Internet of Things: A Comprehensive Survey
Open accessThe DOI matches its Crossref record; 237 of the 237 references it cites were found in a registry or an index; 46 of the 198 sources its claims cite were checked for support.
Abstract
The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may not be feasible in realistic application scenarios due to the high scalability of modern IoT networks and growing data privacy concerns. Federated Learning (FL) has emerged as a distributed collaborative AI approach that can enable many intelligent IoT applications, by allowing for AI training at distributed IoT devices without the need for data sharing. In this article, we provide a comprehensive survey of the emerging applications of FL in IoT networks, beginning from an introduction to the recent advances in FL and IoT to a discussion of their integration. Particularly, we explore and analyze the potential of FL for enabling a wide range of IoT services, including IoT data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy and security. We then provide an extensive survey of the use of FL in various key IoT applications such as smart healthcare, smart transportation, Unmanned Aerial Vehicles (UAVs), smart cities, and smart industry. The important lessons learned from this review of the FL-IoT services and applications are also highlighted. We complete this survey by highlighting the current challenges and possible directions for future research in this booming area.
Overview
CoChat Summary
TL;DR
This survey argues that federated learning (FL) can make IoT systems more privacy-preserving, scalable, and communication-efficient by training models on distributed devices instead of centralizing raw data. It reviews FL in IoT services and applications, then summarizes lessons learned and open research challenges.
Key findings
- FL is presented as an alternative to raw-data sharing in IoT: it enables “privacy-enhanced and scalable data sharing” and keeps raw data local while sharing learning results.
- The survey identifies several IoT service areas where FL is useful: data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy/security.
- It also surveys FL in major application domains: smart healthcare, smart transportation, UAVs, smart city, and smart industry.
- In the paper’s taxonomy tables, several reported results include:
- IoT video data sharing with FL achieved 3.8% higher image-classification accuracy and 1.1% better object-detection performance over conventional FedAvg.
- A UAV-swarm FL scheme reduced the convergence round by 35% compared with non-joint schemes.
- A mobile crowdsensing FL scheme reported over 98% accuracy, with 23.9% runtime reduction and 33.3% communication-latency reduction for gradient aggregation.
Methods
- This is a narrative survey, not an experimental study: it synthesizes prior FL and IoT literature and organizes it by service type, application domain, and FL architecture.
- The paper’s structure includes an overview of FL and IoT, then sections on FL for IoT services and FL for IoT applications, followed by lessons learned and research challenges.
- It also uses taxonomy tables to summarize prior work, including FL type, ML type, FL clients, FL aggregator, key contributions, and limitations.
Limitations
- The paper itself states that existing work leaves several areas insufficiently covered, motivating this survey; it says prior surveys did not provide a comprehensive review of FL in IoT networks and applications.
- It states that many FL-IoT problems remain open, including threats/security, communication and convergence issues, resource management, and the feasibility of deploying AI on constrained IoT sensors.
- Evident from the text: this is a high-level survey with no new dataset, no controlled experiment, and no direct empirical validation of the reviewed methods by the authors themselves.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





![Fig. 6 The architecture of federated learning-based data sharing for IoV with blockchain [52].](https://figures.cochat.ai/paper-figures/2558776f41b74540a5589e277f2ecf12/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-6.png)



![Fig. 10 Federated learning for smart healthcare: A case study for COVID-19 image classification with blockchain [128].](https://figures.cochat.ai/paper-figures/cc15722ada484d9c8d1ca77ec766f832/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-10.png)
![Fig. 11 Federated learning for UAV-based ground air quality monitoring [147].](https://figures.cochat.ai/paper-figures/4f905cb13a204d8fb7509bdec6f7b641/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-11.png)
![Fig. 12 Federated learning for cooperative industry [161].](https://figures.cochat.ai/paper-figures/690f5ab552054933b49389363afcd6da/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-12.png)
Verification
Claims the paper makes
40 Valid · 7 Not valid · 135 Not checked · 63 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Moreover, the cooperation of IoT devices under the guidance of the FL process is able to improve the overall training accuracy of the learning model.”
What the sources say
- Disputedcites [59] [59] J. Ren, H. Wang, T. Hou, S. Zheng, and C. Tang, 'Federated LearningBased Computation Offloading Optimization in Edge ComputingSupported Internet of Things,' IEEE Access , vol. 7, pp. 69 194-69 201, 2019. - sourceExperimental — accuracy not yet measured
The Training Performance Under Different Tasks Probabilities section says FL-based training loses a small amount of model accuracy compared with centralized DRL training, rather than improving it. The Algorithm 1 discussion reports that FL-based training approaches centralized DRL performance after several model aggregations, not that cooperation improves training accuracy. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Due to the contemporary features, DFL can be integrated with P2Pbased communication technologies such as blockchain [37] to build decentralized FL systems.”
What the sources say
- Partly supportedcites [37] [37] D. C. Nguyen, P. N. Pathirana, M. Ding, and A. Seneviratne, 'Integration of Blockchain and Cloud of Things: Architecture, Applications and Challenges,' IEEE Communications Surveys & Tutorials , pp. 1-1, 2020. - sourceExperimental — accuracy not yet measured
The “Peer-to-Peer Learning” section (page unavailable) describes fully decentralized federated learning in which clients communicate with neighboring clients without a central server. It does not identify blockchain as a communication technology for such a system or discuss integrating it with decentralized federated learning. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“To overcome these challenges, FL comes as a natural solution to perform attack detection algorithms for distributed IoT networks [82].”
- Also stated in: § A. Lessons Learned from FL-IoT Services · plain
“FL comes as a natural solution to perform attack detection algorithms for distributed IoT networks [82].”
What the sources say
- Supportedcites [82] [82] T. D. Nguyen, S. Marchal, M. Miettinen, H. Fereidooni, N. Asokan, and A.-R. Sadeghi, 'D ¨ IoT: A Federated Self-learning Anomaly Detection System for IoT,' in Proceedings of the International Conference on Distributed Computing Systems (ICDCS) , Dallas, TX, USA, Jul. 2019, pp. 756-767. - source
Section IV, “Federated Learning Approach,” says the system learns anomaly-detection models from traffic collected at gateways monitoring separate IoT networks and chooses federated learning because data are distributed and each client has little data. The paper thus supports using federated learning for attack detection in distributed IoT networks; “natural solution” is the citing authors’ characterization. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Also stated in: § A. Lessons Learned from FL-IoT Services · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Simulations from different offloading task probabilities indicate an improvement in the offloading performance in terms of high system utility and low task transmission latency.”
What the sources say
- Partly supportedcites [59] [59] J. Ren, H. Wang, T. Hou, S. Zheng, and C. Tang, 'Federated LearningBased Computation Offloading Optimization in Edge ComputingSupported Internet of Things,' IEEE Access , vol. 7, pp. 69 194-69 201, 2019. - sourceExperimental — accuracy not yet measured
In “Training Performance Under Different Tasks Probabilities” (page not provided), the simulations report higher average utility for FL than for centralized DRL. They do not show consistently lower task transmission time: it is similar at low task-generation probabilities and higher for FL at probabilities of 0.7–0.9. The claim overstates the transmission-latency result. (LLM, conf=0.89)
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In traditional IoT systems [39], [40], AI functions are often placed on data centers or cloud servers, which is obviously not scalable to the exponential growth of IoT devices and the high data distribution of large-scale IoT networks.”
What the sources say
- Partly supportedcites [39] [39] M. Mohammadi, A. Al-Fuqaha, S. Sorour, and M. Guizani, 'Deep Learning for IoT Big Data and Streaming Analytics: A Survey,' IEEE Communications Surveys & Tutorials , vol. 20, no. 4, pp. 2923-2960, 2018. - sourceExperimental — accuracy not yet measured
Section VI (page unavailable) says IoT analytics tasks are currently performed in the cloud and that moving some analytics closer to devices can avoid transmitting large amounts of data to distant cloud nodes. It does not say cloud-based AI is inherently unable to scale with IoT growth or distributed data; the Enabling Technologies and Platforms subsection instead calls scalable cloud-centric analytics for massive IoT data an important research area. (LLM, conf=0.86)
- Not checked yetcites [40] [40] D. C. Nguyen, P. Cheng, M. Ding, D. Lopez-Perez, P. N. Pathirana, J. Li, A. Seneviratne, Y. Li, and H. V. Poor, 'Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective,' IEEE Communications Surveys & Tutorials , pp. 1-1, Sep. 2020. - source
Checked before — its earlier verdict is held back until a new check runs.
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
107 more claims · 22 with their cited sources checked
Create a free account to see all 245 claims and to verify the 59 references still open.
- Probably not a substantial claim. 56
- It may state two separate claims as one. 89
- The quote only partly states this claim. 2
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
“This assures that sensitive data never leave the device or institution, preserving privacy and reducing the risks associated with data breaks [7].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [7]
Experimental — accuracy not yet measured
Citations
Cites
Items 201–237 of 237
FC-SLAM: Federated Learning Enhanced Distributed Visual-LiDAR SLAM In Cloud Robotic System
Li, Z., Wang, L., Jiang, L., & Xu, C.-Z. (2019) · 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961798 · Cited by 28 · cited 1×
“Enabled by the FL-based IoT localization concept as presented in subsection III-D, a federated Simultaneous Localization and Mapping (SLAM) system with cloud computing is deployed in [167].”
MethodPrivacy-Preserving Personalized Federated Learning
Hu, R., Guo, Y., Li, H., Pei, Q., & Gong, Y. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149207 · Cited by 28
Federated Learning for Ultra-Reliable Low-Latency V2V Communications
Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2018) · 2018 IEEE Global Communications Conference (GLOBECOM) · doi:10.1109/glocom.2018.8647927 · Cited by 25 · cited 3×
“Further, FL has the potential to facilitate resource management strategies for vehicle-to-vehicle (V2V) networks [134].”
BackgroundInfluentialCommunication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
Park, J., Samarakoon, S., Elgabli, A., Kim, J., Bennis, M., Kim, S.-L., & Debbah, M. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3055679 · Cited by 25
Lim, W. Y. B., Huang, J., Xiong, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03877 · Cited by 24
Robust Pervasive Detection for Adversarial Samples of Artificial Intelligence in IoT Environments
Wang, S., & Qiao, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2919695 · Cited by 23
MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
Zhang, Y., Gu, T., & Zhang, X. (2020) · 2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn48710.2020.00-45 · Cited by 23 · cited 2×
“To reduce latency spent by communications among FL clients and the server, a new chain-directed Synchronous Stochastic Gradient Descent approach is introduced in [122] for personal”
BackgroundMethodLearn electronic health records by fully decentralized federated learning
Lu, S., Zhang, Y., Wang, Y., & Mack, C. (2019) · arXiv · doi:10.48550/arxiv.1912.01792 · Cited by 23
Lim, H.-K., Kim, J.-B., Kim, C.-M., Hwang, G.-Y., Choi, H.-B., & Han, Y.-H. (2020) · 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic48513.2020.9065233 · Cited by 22 · cited 4×
“Edge computing is also integrated with FL in [166] to realize a collaborative learning among robotic arm devices.”
BackgroundMethodInfluentialVFL: A Verifiable Federated Learning with Privacy-Preserving for Big Data in Industrial IoTPreprint
Fu, A., Zhang, X., Xiong, N. N., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13585 · Cited by 22
Yin, F., Lin, Z., Xu, Y., Kong, Q., Li, D., Theodoridis, S., Shuguang, & Cui (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03697 · Cited by 22
Blockchain and AI-based Solutions to Combat Coronavirus (COVID-19)-like Epidemics: A Survey
Nguyen, D., Ding, M., Pathirana, P. N., et al. (2020) · doi:10.36227/techrxiv.12121962.v1 · Cited by 22
Self-citationLearning Cooperation Schemes for Mobile Edge Computing Empowered Internet of Vehicles
Cao, J., Zhang, K., Wu, F., & Leng, S. (2020) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc45663.2020.9120493 · Cited by 17
Task Allocation for Mobile Federated and Offloaded Learning with Energy and Delay Constraints
Mohammad, U., Sorour, S., & Hefeida, M. (2020) · 2020 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops49005.2020.9145450 · Cited by 16 · cited 4×
“an overall offloading target, such as offloading latency minimization [44].”
BackgroundMethodInfluentialPredictive GPU-based ADAS Management in Energy-Conscious Smart Cities
Perez, S., Perez, J., Arroba, P., Blanco, R., Ayala, J. L., & Moya, J. M. (2019) · 2019 IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc246665.2019.9071685 · Cited by 16
A Review of Privacy-preserving Federated Learning for the Internet-of-ThingsPreprint
Briggs, C., Fan, Z., & Andras, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11794 · Cited by 16
Determining the Breakpoints of Fundamental Diagrams
Jin, S., Luo, X., & Ma, D. (2020) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2018.2876576 · Cited by 15 · cited 1×
“Simulation results from using a Caltrans Performance Measurement System (PeMS) database [132] show less accuracy degradation and high privacy levels over centralized learning methods.”
MethodWang, Y., Yang, Y., & Luo, T. (2020) · 2020 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops49005.2020.9145090 · Cited by 13 · cited 3×
“Another work in [145] focuses on developing a convolutional auto-encoder based on FL for illumination distribution in UAV communications.”
BackgroundMethodInfluentialModelling Audiological Preferences using Federated Learning
Szatmari, T.-I., Petersen, M. K., Korzepa, M. J., & Giannetsos, T. (2020) · Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization · doi:10.1145/3386392.3399560 · Cited by 12 · cited 1×
“Smartphones have been utilized in [123] to implement an FL algorithm for federated mobile healthcare, with a focus on solving the cold start issue caused by slow data generation and computation of certain mobile devices in the cooperative FL process.”
MethodMulti-Dimensional Contract-Matching for Federated Learning in UAV-Enabled Internet of Vehicles
Lim, W. Y. B., Huang, J., Xiong, Z., Kang, J., Niyato, D. T., Hua, X., Leung, C., & Miao, C. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322548 · Cited by 12
Ubiquitous Computing and Distributed Machine Learning in Smart Cities
Mukhametov, D. R. (2020) · 2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) · doi:10.1109/weconf48837.2020.9131518 · Cited by 11 · cited 2×
“To overcome the challenges posed by the ubiquity of smart city data from different streams and devices and user privacy concerns, FL is also used in [153] to structure data streams from ubiquitous IoT devices that act as FL clients to perform local learning without sharing their data to external third-parties.”
BackgroundDistributed and Scalable Intrusion Detection System Based on Agents and Intelligent Techniques
El-Semary, A. M., & Mostafa, M. G. M. (2010) · Journal of Information Processing Systems · doi:10.3745/jips.2010.6.4.481 · Cited by 10 · cited 2×
“To improve the scalability of intrusion detection, a line-speed and scalable FL approach is introduced in [85].”
MethodFully Decentralized Federated Learning Based Beamforming Design for UAV CommunicationsPreprint
Xiao, Y., Yu, Y., Huang, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13614 · Cited by 10
Towards energy efficient federated learning over 5G+ mobile devices
Shi, D., Li, L., Chen, R., Prakash, P., Pan, M., & Fang, Y. (2021) · arXiv · doi:10.48550/arxiv.2101.04866 · Cited by 9
Empowering the Edge Intelligence by Air-Ground Integrated Federated LearningPreprint
Qu, Y., Dong, C., Zheng, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13054 · Cited by 8
Intelligent Task Offloading for Heterogeneous V2X CommunicationsPreprint
Xiong, K., Leng, S., Huang, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15855 · Cited by 7
Cloud-based federated boosting for mobile crowdsensing
Wang, Z., Yang, Y., Liu, Y., Liu, X., Gupta, B. B., & Ma, J. (2020) · arXiv · doi:10.48550/arxiv.2005.05304 · Cited by 6
Poster Abstract: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
Zhang, Y., Gu, T., & Zhang, X. (2020) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn48710.2020.00-24 · Cited by 1
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Li, Q., Wen, Z., Wu, Z., et al. (2019) · arXiv · doi:10.48550/arxiv.1907.09693
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
Park, J., Samarakoon, S., Elgabli, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2008.02608
Federated Learning for 6G Communications: Challenges, Methods, and Future Directions
Liu, Y., Yuan, X., Xiong, Z., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.02931
Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning
Rodríguez-Barroso, N., Martínez-Cámara, E., Luzón, M. V., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.15030
Less is More: A privacy-respecting Android malware classifier using Federated Learning
Gálvez, R., Moonsamy, V., & Diaz, C. (2020) · arXiv · doi:10.48550/arxiv.2007.08319
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT Imaging
Kumar, R., Khan, A. A., Zhang, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.06537
Federated Learning in Vehicular Networks
Elbir, A. M., Soner, B., Coleri, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.01412
Shiri, H., Park, J., & Bennis, M. (2020) · arXiv · doi:10.48550/arxiv.2003.04451
FedAR: Activity and Resource-Aware Federated Learning Model for Distributed Mobile Robots
Imteaj, A., & Amini, M. H. (2021) · arXiv · doi:10.48550/arxiv.2101.03705
Research works printed but not linked: 5
- 2020, Cisco Global Cloud Index Forecast and Methodology 2016–2021 White Paper
- xu, 2019, ELFISH Resource-aware federated learning on heterogeneous edge devices
- rodriguez-barroso, 2020, Dynamic federated learning model for identifying adversarial clients
- cai, 2020, TinyTL: Reduce memory, not parameters for efficient on-device learning, Proc Adv Neural Inf Process Syst, 33
- giust, 2017, Multi access edge computing overview of ETSI–IEEE future networks, IEEE 5G Tech Focus, 1, 4
Cited by
6G Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., Niyato, D., Dobre, O., & Poor, H. V. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3103320 · Cited by 1,452
“Nevertheless, the communication latency caused by packet loss checking over satellite channels has not been considered in the proposed multiuser satellite IoT system optimization.”
BackgroundSelf-citationFederated learning for smart healthcare: A survey
Nguyen, D. C., Pham, Q.-V., Pathirana, P. N., Ding, M., Seneviratne, A., Lin, Z., Dobre, O., & Hwang, W.-J. (2023) · ACM Computing Surveys · doi:10.1145/3501296 · Cited by 827
Self-citationXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
“Additionally, by collecting large and diverse datasets from many devices, FL also improves the convergence rate of training and obtains an accurate global model [61].”
Cellular, Wide-Area, and Non-Terrestrial IoT: A Survey on 5G Advances and the Road Toward 6G
Vaezi, M., Azari, A., Khosravirad, S. R., Shirvanimoghaddam, M., Azari, M. M., Chasaki, D., & Popovski, P. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3151028 · Cited by 631
Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges
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. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3315746 · Cited by 625
“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.”
Metadata
- Authors
- Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H.
- Affiliations
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Data61 (AU)
- Deakin University (AU)
- UNSW Sydney (AU)
- Nanjing University of Science and Technology (CN)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2021
- Volume
- 23
- Issue
- 3
- Pages
- 1622-1658
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W3155912831
- Cited by
- 1,503
- References
- 171
- Citations by year
- 2026: 325 · 2025: 458 · 2024: 359 · 2023: 243 · 2022: 106 · 2021: 16
- FWCI
- 96.12
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- CSIRO Data61, Australia
- U.S. National Science Foundation (CCF-1908308)
- National Natural Science Foundation of China (61872184)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Science Applications › Mobile Crowdsensing and Crowdsourcing
- Keywords
- federated learning, Internet of Things, distributed learning, data privacy, data offloading, caching, attack detection, localization
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.