Skip to content
2000
Volume 18, Issue 10
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

In the field of machine learning, federated learning (FL) has become a breakthrough paradigm, provided a decentralized method of training models while solving issues with data security, privacy, and scalability. This study offers a thorough analysis of FL, including an examination of its underlying theories, its varieties, and a comparison with more conventional machine learning techniques. We explore the drawbacks of conventional machine learning techniques, especially when sensitive and distributed data is involved. We also explain how FL addresses these drawbacks by leveraging collaborative learning across decentralized devices or servers. We also highlight the various fields in which FL finds application, including healthcare, industries, IoT, mobile devices, and education, demonstrating its potential to deliver tailored services and predictive analytics while maintaining data privacy. Furthermore, we address the main obstacles to FL adoption, such as costly communication, heterogeneous systems, statistical heterogeneity, and privacy concerns, and we suggest possible directions for future research to effectively overcome these obstacles. In order to facilitate future study and growth in this quickly developing discipline, this review attempts to shed light on the advances and challenges of FL.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/raeeng/10.2174/0123520965328724241218110637
2025-01-15
2026-01-03

  • From This Site

    /content/journals/raeeng/10.2174/0123520965328724241218110637
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. ManglaU. Application of federated learning in telecommunications and edge computing.Federated Learning: A Comprehensive Overview of Methods and Applications.ChamSpringer International Publishing202252353410.1007/978‑3‑030‑96896‑0_25
     [Google Scholar]
  2. NairD.G. RameshC.K. SharmaR. RaoS.K. Exploring SVM for federated machine learning applications.Advances in Distributed Computing and Machine Learning. Lecture Notes in Networks and Systems202242710.1007/978‑981‑19‑1018‑0_25
     [Google Scholar]
  3. ZhangT. GaoL. HeC. ZhangM. KrishnamachariB. AvestimehrA.S. Federated learning for the internet of things: Applications, challenges, and opportunities.IEEE Internet of Things Magazine202251242910.1109/IOTM.004.2100182
     [Google Scholar]
  4. LiuF. LiM. LiuX. XueT. RenJ. ZhangC. A review of federated meta-learning and its application in cyberspace security.Electronics20231215329510.3390/electronics12153295
     [Google Scholar]
  5. ShaheenM. FarooqM.S. UmerT. KimB-S. Applications of federated learning; Taxonomy, challenges, and research trends.Electronics202211467010.3390/electronics11040670
     [Google Scholar]
  6. RatnayakeH. ChenL. DingX. A review of federated learning: taxonomy, privacy and future directions.J. Intell. Inf. Syst.202361392394910.1007/s10844‑023‑00797‑x
     [Google Scholar]
  7. GuanH. YapP-T. BozokiA. LiuM. Federated learning for medical image analysis: A survey.Pattern Recognit.202415111042410.1016/j.patcog.2024.110424
     [Google Scholar]
  8. ZhangJ. LiuL. XuZ. ZhangY. Recent trends in federated learning: A survey.J. Mach. Learn. Res.2023241234256
     [Google Scholar]
  9. MaX. ZhuX. YangC. Federated learning for healthcare: A survey on enabling technologies, challenges, and applications.IEEE Access2023111234512358
     [Google Scholar]
  10. ZhangT. LiuL. XuJ. Adversarial attacks against federated learning: A survey.IEEE Access202085439254403
     [Google Scholar]
  11. LyuL. YuH. YangQ. Threats to federated learning: A survey.IEEE Internet Things J.202081290609079
     [Google Scholar]
  12. KairouzP McMahanHB AventB BelletA BennisM BhagojiAN Advances and open problems in federated learning.202110.1561/9781680837896
     [Google Scholar]
  13. HsuW. EvansR. GeS. LiX. LiuY. RiekeN. Federated learning for healthcare: Applications, challenges, and future directions.IEEE Trans. Med. Imaging202241511921206
     [Google Scholar]
  14. KimM. ParkJ. LeeS. ChoiH. JungK. ChoJ. A survey on federated learning defenses in medical image analysis.J. Med. Inform.2023453225238
     [Google Scholar]
  15. PatelD. SinghR. SharmaV. NairS. GuptaK. DesaiP. Trustworthy federated learning: Emerging challenges and solutions in medical image analysis.J. AI Res.2024602305330
     [Google Scholar]
  16. ShokriR. ShmatikovV. Privacy-Preserving Deep Learning.Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security 2015, pp. 1310-1321.
     [Google Scholar]
  17. YangQ. LiuY. ChenT. TongY. Federated machine learning: Concept and applications.ACM Trans. Intell. Syst. Technol.201910211910.1145/3298981
     [Google Scholar]
  18. WenJ. ZhangZ. LanY. CuiZ. CaiJ. ZhangW. A survey on federated learning: challenges and applications.Int. J. Mach. Learn. Cybern.202314251353510.1007/s13042‑022‑01647‑y
     [Google Scholar]
  19. GosselinR. VieuL. LoukilF. BenoitA. TamL. SivaramanV. KaafarM.A. Privacy and security in federated learning: A survey.Appl. Sci.20221219990110.3390/app12199901
     [Google Scholar]
  20. JiS. TanY. SaravirtaT. YangZ. LiuY. VasankariL. PanS. LongG. WalidA. Emerging trends in federated learning: from model fusion to federated X learning.Int. J. Mach. Learn. Cybern.20241593769379010.1007/s13042‑024‑02119‑1
     [Google Scholar]
  21. ZhangH. BoschJ. Holmström OlssonH. Engineering federated learning systems: A literature review.11th International Conference, ICSOB 2020, Karlskrona, Sweden, November 16–18, 2021.10.1007/978‑3‑030‑67292‑8_17
     [Google Scholar]
  22. PfitznerB. SteckhanN. ArnrichB. Federated learning in a medical context: A systematic literature review.ACM Trans. Internet Technol.202121213110.1145/3412357
     [Google Scholar]
  23. LoS.K. HuR. XiongS. A comprehensive review on federated machine learning in cloud and edge computing systems.ACM Comput. Surv.2023564134
     [Google Scholar]
  24. AbdulrahmanS. ToutH. Ould-SlimaneH. MouradA. TalhiC. GuizaniM. A survey on federated learning: The journey from centralized to distributed on-site learning and beyond.IEEE Internet Things J.2021875476549710.1109/JIOT.2020.3030072
     [Google Scholar]
  25. KaurH. RaniV. KumarM. SachdevaM. MittalA. KumarK. Federated learning: a comprehensive review of recent advances and applications.Multimedia Tools Appl.20238318541655418810.1007/s11042‑023‑17737‑0
     [Google Scholar]
  26. KonečnýJ. McMahanH.B. YuF. RichtárikP. SureshA.T. BaconD. Federated learning: Strategies for improving communication efficiency.arXiv preprint20162016
     [Google Scholar]
  27. TyagiS. RajputI.S. PandeyR. Federated learning: Applications, security hazards, and defense measures.2023 International Conference on Device Intelligence, Computing and Communication Technologies (DICCT)202310.1109/DICCT56244.2023.10110075
     [Google Scholar]
  28. WangH. KaplanZ. NiuD. LiB. Optimizing federated learning on non-IID data with reinforcement learning.IEEE Trans. Neural Netw. Learn. Syst.2021321340355
     [Google Scholar]
  29. MohammadiM. Al-FuqahaA. Federated learning for vehicular networks: A review and case study.IEEE Trans. Intell. Transp. Syst.202122956065615
     [Google Scholar]
  30. HsiehK. PhanishayeeA. MutluO. GibbonsP.B. The non-IID data problem in federated learning.Proceedings of the 2nd SysML Conference, Palo Alto, CA, USA, 2020.
     [Google Scholar]
  31. ZhaoY. ZhangY. XuJ. HuX. Decentralized federated learning: A comprehensive survey.IEEE Trans. Parallel Distrib. Syst.2023342453469
     [Google Scholar]
  32. ZhangY. ZhaoL. SongS. YanS. XieX. Federated learning with personalized models: Insights, methods, and applications.ACM Comput. Surv.2022553136
     [Google Scholar]
  33. YangC. ShiR. DongX. XiaoZ. SuH. LiS. On the utility-privacy tradeoff of federated learning for smart cities.IEEE Commun. Mag.20215947277
     [Google Scholar]
  34. SunC. KangJ. XiongZ. NiyatoD. Federated learning with blockchain for autonomous vehicles: Opportunities and challenges.IEEE Trans. Intell. Transp. Syst.202324317461757
     [Google Scholar]
  35. LiL. FanY. TseM. LinK.Y. A review of applications in federated learning.Comput. Ind. Eng.202014910685410.1016/j.cie.2020.106854
     [Google Scholar]
  36. ChenY. LuoF. LiT. XiangT. LiuZ. LiJ. A training-integrity privacy-preserving federated learning scheme with trusted execution environment.Inf. Sci.2020522697910.1016/j.ins.2020.02.037
     [Google Scholar]
  37. MothukuriV. PariziR.M. PouriyehS. HuangY. DehghantanhaA. SrivastavaG. A survey on security and privacy of federated learning.Future Gener. Comput. Syst.202111561964010.1016/j.future.2020.10.007
     [Google Scholar]
  38. LiH. LiC. WangJ. YangA. MaZ. ZhangZ. HuaD. Review on security of federated learning and its application in healthcare.Future Gener. Comput. Syst.202314427129010.1016/j.future.2023.02.021
     [Google Scholar]
  39. AbadiM. ChuA. GoodfellowI. McMahanH.B. MironovI. TalwarK. ZhangL. Deep learning with differential privacy.Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp.308-318.10.1145/2976749.2978318
     [Google Scholar]
  40. LuoB. GaoL. XuJ. TianF. LiJ. Cost-effective federated learning design.IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, 2021.
     [Google Scholar]
  41. LiT. SahuA.K. TalwalkarA. SmithV. Federated learning with differential privacy: Algorithms and performance analysis.IEEE Trans. Inf. Forensics Security20211610541069
     [Google Scholar]
  42. LiuY. KangJ. NiyatoD. ElkashlanM. XiongZ. ZhaoX. Federated learning for edge devices: A comprehensive survey.IEEE Commun. Surv. Tutor.202123320462107
     [Google Scholar]
  43. VucinichS. ZhuQ. The current state and challenges of fairness in federated learning.IEEE Access202311809038091410.1109/ACCESS.2023.3295412
     [Google Scholar]
  44. NguyenT. TuyenH. BaoL. PhanD. A federated learning framework for privacy-preserving machine learning in healthcare.J. Biomed. Inform.2023138104328
     [Google Scholar]
  45. BeltránE.T.M. SharmaP. Sanz-BobiM.A. SuriN. Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges.IEEE Commun. Surv. Tutor.2023
     [Google Scholar]
  46. WuY. ZhaoW. LiuY. ChenX. Personalized federated learning under mixture of distributions.Proceedings of the International Conference on Machine Learning2023
     [Google Scholar]
  47. PandyaS. SrivastavaG. JhaveriR. BabuM.R. BhattacharyaS. MaddikuntaP.K.R. MastorakisS. PiranM.J. GadekalluT.R. Federated learning for smart cities: A comprehensive survey.Sustain. Energy Technol. Assess.20235510298710.1016/j.seta.2022.102987
     [Google Scholar]
  48. HuangW. ZhangJ. YuS. Rethinking federated learning with domain shift: A prototype view.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)202310.1109/CVPR52729.2023.01565
     [Google Scholar]
  49. LiQ. ChenY. ZhangY. JinR. Fedtree: A federated learning system for trees.Proceedings of Machine Learning and Systems20235218230
     [Google Scholar]
  50. ReddyC.K. NarendraN.N. Federated learning: Collaborative machine learning without centralized training data.ACM Comput. Surv.2023
     [Google Scholar]
  51. WuX. HuangF. HuZ. HuangH. Faster adaptive federated learning.Proc. Conf. AAAI Artif. Intell.2023379103791038710.1609/aaai.v37i9.26235
     [Google Scholar]
  52. KharitonovE. Federated online learning to rank with evolution strategies.Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining201910.1145/3289600.3290968
     [Google Scholar]
  53. MaS. LiuJ. ZuoX. A review of graph neural networks.J. Comput. Res. & Develop.20225914780
     [Google Scholar]
  54. HalderS. GhosalA. ContiM. Efficient physical intrusion detection in Internet of Things: A Node deployment approach.Comput. Netw.2019154284610.1016/j.comnet.2019.02.019
     [Google Scholar]
  55. NaseerS. SaleemY. Enhanced network intrusion detection using deep convolutional neural networks.KSII Trans. Internet Inf. Syst.2018121051595178
     [Google Scholar]
  56. ThummisettiB.S.P. AtluriH. Advancing healthcare informatics for empowering privacy and security through federated learning paradigms.IJSDCS202411116
     [Google Scholar]
  57. ZhaoY. ChenJ. WuD. TengJ. YuS. Multi-task network anomaly detection using federated learning.Proceedings of the 10th International Symposium on Information and Communication Technology (SoICT ’19), 2019, pp.273-279.10.1145/3368926.3369705
     [Google Scholar]
  58. LiB. WuY. SongJ. LuR. LiT. ZhaoL. DeepFed: Federated deep learning for intrusion detection in industrial cyber–physical systems.IEEE Trans. Industr. Inform.20211785615562410.1109/TII.2020.3023430
     [Google Scholar]
  59. LiuR. XingP. DengZ. LiA. GuanC. YuH. Federated graph neural networks: Overview, techniques, and challenges.IEEE Trans. Neural Netw. Learn. Syst.202411710.1109/TNNLS.2024.3360429
     [Google Scholar]
  60. Martínez BeltránE.T. Perales GómezÁ.L. FengC. Sánchez SánchezP.M. López BernalS. BovetG. Gil PérezM. Martínez PérezG. Huertas CeldránA. Fedstellar: A platform for decentralized federated learning.Expert Syst. Appl.202424212286110.1016/j.eswa.2023.122861
     [Google Scholar]
  61. LiuY. KangY. ZouT. PuY. HeY. YeX. OuyangY. ZhangY-Q. YangQ. Vertical federated learning: Concepts, advances, and challenges.IEEE Trans. Knowl. Data Eng.20243673615363410.1109/TKDE.2024.3352628
     [Google Scholar]
  62. FengB. ShiJ. HuangL. YangZ. FengS-T. LiJ. ChenQ. XueH. ChenX. WanC. HuQ. CuiE. ChenY. LongW. Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence.Nat. Commun.202415174210.1038/s41467‑024‑44946‑4
     [Google Scholar]
  63. ChaiD. WangL. YangL. ZhangJ. ChenK. YangQ. A survey for federated learning evaluations: Goals and measures.IEEE Trans. Knowl. Data Eng.202436105007502410.1109/TKDE.2024.3382002
     [Google Scholar]
  64. MoraA. BujariA. BellavistaP. Enhancing generalization in Federated Learning with heterogeneous data: A comparative literature review.Future Gener. Comput. Syst.202415711510.1016/j.future.2024.03.027
     [Google Scholar]
  65. SunY. ShenL. TaoD. Understanding how consistency works in federated learning via stage-wise relaxed initialization.Adv. Neural Inf. Process. Syst.2024202436
     [Google Scholar]
  66. ZhangH. ZhaoH. TangZ. ZhouY. WuB. A3FL: Adversarially adaptive backdoor attacks to federated learning.Adv. Neural Inf. Process. Syst.2024202436
     [Google Scholar]
  67. WangS. ZucconG. An analysis of untargeted poisoning attack and defense methods for federated online learning to rank systems.Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval202310.1145/3578337.3605117
     [Google Scholar]
  68. ZhuH. XuJ. LiuS. JinY. YangJ. Federated learning on non-IID data: A survey.Neurocomputing202146537139010.1016/j.neucom.2021.07.098
     [Google Scholar]
  69. LimY.W. HoangD.T. TanS. XieW. Mobile edge computing for federated learning: A survey of trends, challenges, and solutions.IEEE Trans. Mobile Comput.2023223451467
     [Google Scholar]
  70. YuanW. HeK. ChenJ. ZhouJ. Federated unlearning for on-device recommendation.Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 2023.10.1145/3539597.3570463
     [Google Scholar]
  71. BiZ. HeY. LinH. JiangJ. A multi-behavior recommendation algorithm based on personalized federated learning.International Conference on Collaborative Computing: Networking, Applications and Worksharing2023
     [Google Scholar]
  72. BrisimiT.S. OlshevskyA. PaschalidisI.C. Federated learning of predictive models from healthcare data.IEEE Transactions on Medical Informatics.202330512651280
     [Google Scholar]
  73. GafniT. ShlezingerN. CohenK. EldarY.C. PoorH.V. Ben-DavidM. Federated Learning: A signal processing perspective.IEEE Signal Process. Mag.2022393144110.1109/MSP.2021.3125282
     [Google Scholar]
  74. RiekeN. HancoxJ. LiW. MilletarìF. RothH.R. AlbarqouniS. BakasS. GaltierM.N. LandmanB.A. Maier-HeinK. OurselinS. ShellerM. SummersR.M. TraskA. XuD. BaustM. CardosoM.J. The future of digital health with federated learning.NPJ Digit. Med.20203111910.1038/s41746‑020‑00323‑1
     [Google Scholar]
  75. NguyenD.C. DingM. PathiranaP.N. SeneviratneA. LiJ. Vincent PoorH. Federated learning for internet of things: A comprehensive survey.IEEE Commun. Surv. Tutor.20212331622165810.1109/COMST.2021.3075439
     [Google Scholar]
  76. AledhariM. RazzakR. PariziR.M. SaeedF. Federated learning: A survey on enabling technologies, protocols, and applications.IEEE Access2020814069914072510.1109/ACCESS.2020.3013541
     [Google Scholar]
  77. ZhangX. WuX. LiB. LiuY. Privacy-preserving federated learning and applications: A comprehensive review.J. Comput. Secur.202148102232
     [Google Scholar]
  78. ZhengQ. ZhangT. LiuJ. XuW. Secure federated learning with adversarial noise: An overview.IEEE Trans. Neural Netw. Learn. Syst.202334624312444
     [Google Scholar]
  79. LiuL. ZhangK. WangX. WangH. Cross-device federated learning: Challenges, trends, and future research directions.IEEE Access2024121238712404
     [Google Scholar]
  80. LimW.Y.B. LuongN.C. HoangD.T. JiaoY. LiangY.C. YangQ. NiyatoD. MiaoC. Federated learning in mobile edge networks: A comprehensive survey.IEEE Commun. Surv. Tutor.20202232031206310.1109/COMST.2020.2986024
     [Google Scholar]
  81. McMahanB. Communication-Efficient Learning of Deep Networks from Decentralized Data.Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS),2017, 1273-1282.
     [Google Scholar]
  82. XuJ. GlicksbergB.S. SuC. WalkerP. BianJ. WangF. Federated Learning for Healthcare Informatics.J. Healthc. Inform. Res.20215111910.1007/s41666‑020‑00082‑4
     [Google Scholar]
  83. LiT. SahuA.K. TalwalkarA. SmithV. Federated learning: Challenges, methods, and future directions.IEEE Signal Process. Mag.2020373506010.1109/MSP.2020.2975749
     [Google Scholar]
  84. BrisimiT.S. ChenR. MelaT. OlshevskyA. PaschalidisI.C. ShiW. Federated learning of predictive models from federated Electronic Health Records.Int. J. Med. Inform.2018112596710.1016/j.ijmedinf.2018.01.007
     [Google Scholar]
  85. GafniT. Shalev-ShwartzS. KatzirL. Signal processing perspectives in federated learning systems.IEEE Trans. Signal Process.20237120221810.1109/TSP.2023.3242074
     [Google Scholar]
  86. NassifA. AzamS. AbbasA. A review of the future of federated learning in healthcare.IEEE Transactions on Medical Informatics.2023423810822
     [Google Scholar]
  87. FuS. JiaH. VassilakiM. KelothV.K. DangY. ZhouY. GargM. PetersenR.C. St SauverJ. MoonS. WangL. WenA. LiF. XuH. TaoC. FanJ. LiuH. SohnS. FedFSA: Hybrid and federated framework for functional status ascertainment across institutions.J. Biomed. Inform.202415210462310.1016/j.jbi.2024.104623
     [Google Scholar]
  88. ZhangW. WangT. LiX. Enabling federated learning in the industrial internet of things: Challenges, solutions, and future directions.J. Ind. Inf. Integr.202330100380
     [Google Scholar]
  89. NguyenH.T. SehwagV. HosseinalipourS. BrintonC.G. ChiangM. Vincent PoorH. Fast-convergent federated learning.IEEE J. Sel. Areas Comm.202139120121810.1109/JSAC.2020.3036952
     [Google Scholar]
  90. MistryD. MridhaM.F. SafranM. AlfarhoodS. SahaA.K. CheD. Privacy-preserving on-screen activity tracking and classification in e-learning using federated learning.IEEE Access202311793157932910.1109/ACCESS.2023.3299331
     [Google Scholar]
  91. GhimireB. RawatD.B. Recent advances on federated learning for cybersecurity and cybersecurity for federated learning for Internet of Things.IEEE Internet Things J.20229118229824910.1109/JIOT.2022.3150363
     [Google Scholar]
  92. BashirA.K. VictorN. BhattacharyaS. Huynh-TheT. ChengodenR. YenduriG. MaddikuntaP.K.R. PhamQ-V. GadekalluT.R. LiyanageM. Federated learning for the healthcare metaverse: Concepts, applications, challenges, and future directions.IEEE Internet Things J.20231024218732189110.1109/JIOT.2023.3304790
     [Google Scholar]
  93. LongG. YangB. ZhangT. ChenY. ZhouS. Federated learning for open banking.Federated Learning: Privacy and Incentive.ChamSpringer International Publishing202024025410.1007/978‑3‑030‑63076‑8_17
     [Google Scholar]
/content/journals/raeeng/10.2174/0123520965328724241218110637
Loading
Federated Learning: An Approach for Managing Data Privacy and Security in Collaborative Learning
Recent Advances in Electrical & Electronic Engineering 18, 1754 (2025); https://doi.org/10.2174/0123520965328724241218110637
/content/journals/raeeng/10.2174/0123520965328724241218110637
/content/journals/raeeng/10.2174/0123520965328724241218110637
Loading

Data & Media loading...


  • Article Type:     Review Article
Keyword(s): Federated learning; healthcare; IoT; machine learning mobile devices; privacy; security issues

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test