Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020:8:140699-140725.
doi: 10.1109/access.2020.3013541. Epub 2020 Jul 31.

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Mohammed Aledhari  1 , Rehma Razzak  1 , Reza M Parizi  1 , Fahad Saeed  2
Affiliations

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Mohammed Aledhari et al. IEEE Access. 2020.

Abstract

This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on enabling software and hardware platforms, protocols, real-life applications and use-cases. FL can be applicable to multiple domains but applying it to different industries has its own set of obstacles. FL is known as collaborative learning, where algorithm(s) get trained across multiple devices or servers with decentralized data samples without having to exchange the actual data. This approach is radically different from other more established techniques such as getting the data samples uploaded to servers or having data in some form of distributed infrastructure. FL on the other hand generates more robust models without sharing data, leading to privacy-preserved solutions with higher security and access privileges to data. This paper starts by providing an overview of FL. Then, it gives an overview of technical details that pertain to FL enabling technologies, protocols, and applications. Compared to other survey papers in the field, our objective is to provide a more thorough summary of the most relevant protocols, platforms, and real-life use-cases of FL to enable data scientists to build better privacy-preserving solutions for industries in critical need of FL. We also provide an overview of key challenges presented in the recent literature and provide a summary of related research work. Moreover, we explore both the challenges and advantages of FL and present detailed service use-cases to illustrate how different architectures and protocols that use FL can fit together to deliver desired results.

Keywords: Collaborative AI; Decentralized Data; Federated Learning; Machine Learning; On-Device AI; Peer-to-peer network; Privacy; Security.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
General Federated Learning Architecture
Fig. 2.
Fig. 2.
Federated Learning Architecture applied in a hospital setting
Fig. 3.
Fig. 3.
Vertical Federated Learning Arcitecture
Fig. 4.
Fig. 4.
Horizontal Federated Learning Architecture
Fig. 5.
Fig. 5.
Framework of Federated Transfer Learning
Fig. 6.
Fig. 6.
Framework of MMVFL
Fig. 7.
Fig. 7.
FEDF Framework
Fig. 8.
Fig. 8.
Framework of PerFit
Fig. 9.
Fig. 9.
FedHealth Framework
Fig. 10.
Fig. 10.
Framework of FADL
Fig. 11.
Fig. 11.
FL-based framework that incorporates blockchain.
Fig. 12.
Fig. 12.
LoAdaBoost Client-Server Architecture
Fig. 13.
Fig. 13.
Architecture of BrainTorrent Algorithm
Fig. 14.
Fig. 14.
Hybrid-FL Framework
Fig. 15.
Fig. 15.
FedCS protocol framework
Fig. 16.
Fig. 16.
VerifyNet Architecture
Fig. 17.
Fig. 17.
Traffic Flow diagram. This illustrates how difficult traffic flow prediction can be due to data not being able to be shared.
Fig. 18.
Fig. 18.
Complete Framework of ATMOSPHERE
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Liang PP, Liu T, Liu Z, Salakhutdinov R, and Morency L-P, “Think locally, act globally: Federated learning with local and global representations,” ArXiv, vol. abs/2001.01523, 2020.
    1. Zhuo HH, Feng W, Lin Y, Xu Q, and Yang Q, “Federated deep reinforcement learning,” 2019.
    1. Yu H, Liu Z, Liu Y, Chen T, Cong M, Weng X, Niyato D, and Yang Q, “A fairness-aware incentive scheme for federated learning,” in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2020, pp. 393–399.
    1. Truex S, Baracaldo N, Anwar A, Steinke T, Ludwig H, Zhang R, and Zhou Y, “A hybrid approach to privacy-preserving federated learning,” in Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, 2019, pp. 1–11.
    1. SÜZEN AA and ŞİMŞEK MA, “A novel approach to machine learning application to protection privacy data in healthcare: Federated learning,” Namık Kemal Tıp Dergisi, vol. 8, no. 1, pp. 22–30.

LinkOut - more resources