IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2310.13681.html
   My bibliography  Save this paper

RealFM: A Realistic Mechanism to Incentivize Federated Participation and Contribution

Author

Listed:
  • Marco Bornstein
  • Amrit Singh Bedi
  • Anit Kumar Sahu
  • Furqan Khan
  • Furong Huang

Abstract

Edge device participation in federating learning (FL) is typically studied under the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in realistic settings, with many encountering the free-rider dilemma. In a step to push FL towards realistic settings, we propose RealFM: the first federated mechanism that (1) realistically models device utility, (2) incentivizes data contribution and device participation, (3) provably removes the free-rider dilemma, and (4) relaxes assumptions on data homogeneity, data sharing, and monetary reward payments. Compared to previous FL mechanisms, RealFM allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices. On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.

Suggested Citation

  • Marco Bornstein & Amrit Singh Bedi & Anit Kumar Sahu & Furqan Khan & Furong Huang, 2023. "RealFM: A Realistic Mechanism to Incentivize Federated Participation and Contribution," Papers 2310.13681, arXiv.org, revised Feb 2024.
    • Handle: RePEc:arx:papers:2310.13681
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2310.13681
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sai Praneeth Karimireddy & Wenshuo Guo & Michael I. Jordan, 2022. "Mechanisms that Incentivize Data Sharing in Federated Learning," Papers 2207.04557, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    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. Baihe Huang & Sai Praneeth Karimireddy & Michael I. Jordan, 2023. "Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning," Papers 2306.05592, arXiv.org.
    2. Alireza Fallah & Michael I. Jordan & Ali Makhdoumi & Azarakhsh Malekian, 2024. "On Three-Layer Data Markets," Papers 2402.09697, arXiv.org, revised Feb 2024.

    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:arx:papers:2310.13681. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.