IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v14y2023i1d10.1038_s41467-023-38569-4.html
   My bibliography  Save this article

Decentralized federated learning through proxy model sharing

Author

Listed:
  • Shivam Kalra

    (Layer 6 AI
    University of Waterloo
    Vector Institute)

  • Junfeng Wen

    (Carleton University, School of Computer Science)

  • Jesse C. Cresswell

    (Layer 6 AI)

  • Maksims Volkovs

    (Layer 6 AI)

  • H. R. Tizhoosh

    (University of Waterloo
    Vector Institute
    Mayo Clinic)

Abstract

Institutions in highly regulated domains such as finance and healthcare often have restrictive rules around data sharing. Federated learning is a distributed learning framework that enables multi-institutional collaborations on decentralized data with improved protection for each collaborator’s data privacy. In this paper, we propose a communication-efficient scheme for decentralized federated learning called ProxyFL, or proxy-based federated learning. Each participant in ProxyFL maintains two models, a private model, and a publicly shared proxy model designed to protect the participant’s privacy. Proxy models allow efficient information exchange among participants without the need of a centralized server. The proposed method eliminates a significant limitation of canonical federated learning by allowing model heterogeneity; each participant can have a private model with any architecture. Furthermore, our protocol for communication by proxy leads to stronger privacy guarantees using differential privacy analysis. Experiments on popular image datasets, and a cancer diagnostic problem using high-quality gigapixel histology whole slide images, show that ProxyFL can outperform existing alternatives with much less communication overhead and stronger privacy.

Suggested Citation

  • Shivam Kalra & Junfeng Wen & Jesse C. Cresswell & Maksims Volkovs & H. R. Tizhoosh, 2023. "Decentralized federated learning through proxy model sharing," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
  • Handle: RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-38569-4
    DOI: 10.1038/s41467-023-38569-4
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-023-38569-4
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-023-38569-4?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Stefanie Warnat-Herresthal & Hartmut Schultze & Krishnaprasad Lingadahalli Shastry & Sathyanarayanan Manamohan & Saikat Mukherjee & Vishesh Garg & Ravi Sarveswara & Kristian Händler & Peter Pickkers &, 2021. "Swarm Learning for decentralized and confidential clinical machine learning," Nature, Nature, vol. 594(7862), pages 265-270, June.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Edward H. Lee & Michelle Han & Jason Wright & Michael Kuwabara & Jacob Mevorach & Gang Fu & Olivia Choudhury & Ujjwal Ratan & Michael Zhang & Matthias W. Wagner & Robert Goetti & Sebastian Toescu & Se, 2024. "An international study presenting a federated learning AI platform for pediatric brain tumors," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    2. Yehui Li & Dalin Qin & H. Vincent Poor & Yi Wang, 2024. "Introducing edge intelligence to smart meters via federated split learning," Nature Communications, Nature, vol. 15(1), pages 1-14, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tao Qi & Fangzhao Wu & Chuhan Wu & Liang He & Yongfeng Huang & Xing Xie, 2023. "Differentially private knowledge transfer for federated learning," Nature Communications, Nature, vol. 14(1), pages 1-9, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-38569-4. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.