IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v14y2022i5p138-d806847.html
   My bibliography  Save this article

A Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices

Author

Listed:
  • Zheyi Chen

    (Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA)

  • Weixian Liao

    (Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA)

  • Pu Tian

    (Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA)

  • Qianlong Wang

    (Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA)

  • Wei Yu

    (Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA)

Abstract

Distributed machine learning paradigms have benefited from the concurrent advancement of deep learning and the Internet of Things (IoT), among which federated learning is one of the most promising frameworks, where a central server collaborates with local learners to train a global model. The inherent heterogeneity of IoT devices, i.e., non-independent and identically distributed (non-i.i.d.) data, and the inconsistent communication network environment results in the bottleneck of a degraded learning performance and slow convergence. Moreover, most weight averaging-based model aggregation schemes raise learning fairness concerns. In this paper, we propose a peer-to-peer decentralized learning framework to tackle the above issues. Particularly, each local client iteratively finds a learning pair to exchange the local learning model. By doing this, multiple learning objectives are optimized to advocate for learning fairness while avoiding small-group domination. The proposed fairness-aware approach allows local clients to adaptively aggregate the received model based on the local learning performance. The experimental results demonstrate that the proposed approach is capable of significantly improving the efficacy of federated learning and outperforms the state-of-the-art schemes under real-world scenarios, including balanced-i.i.d., unbalanced-i.i.d., balanced-non.i.i.d., and unbalanced-non.i.i.d. environments.

Suggested Citation

  • Zheyi Chen & Weixian Liao & Pu Tian & Qianlong Wang & Wei Yu, 2022. "A Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices," Future Internet, MDPI, vol. 14(5), pages 1-18, April.
  • Handle: RePEc:gam:jftint:v:14:y:2022:i:5:p:138-:d:806847
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/14/5/138/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1999-5903/14/5/138/
    Download Restriction: no
    ---><---

    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:gam:jftint:v:14:y:2022:i:5:p:138-:d:806847. 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.

    We have no bibliographic references for this item. You can help adding them by using 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.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.