Client Drift

Client Drift is a phenomenon in federated learning where local model updates from clients deviate from the global optimization direction due to statistical heterogeneity across decentralized data distributions, resulting in biased or inconsistent convergence.

21

Publications

2K

Citations

86

Authors

35

Institutions

Publications per year

2017–2026

19

Authors

86

  1. SP
    Sai Praneeth Karimireddy

    École Polytechnique Fédérale de Lausanne, Switzerland

    3 publications · 1K citations

    3

    h-index

  2. AT
    Ananda Theertha Suresh

    Google (United States), United States

    2 publications · 309 citations

    2

    h-index

  3. AM
    Axiu Mao

    City University of Hong Kong, Hong Kong SAR China

    2 publications · 34 citations

    2

    h-index

  4. AX
    An Xu

    University of Pittsburgh, United States

    2 publications · 80 citations

    2

    h-index

  5. HH
    Heng Huang

    The University of Texas at Arlington, United States

    2 publications · 80 citations

    2

    h-index

1–5 of 86

Venues

  1. arXiv (Cornell University)

    Repository · 5 publications · 902 citations

    5

    h-index

  2. IEEE Internet of Things Journal

    2 publications · 157 citations

    2

    h-index

  3. Journal of Consulting and Clinical Psychology

    1 publications · 149 citations

    1

    h-index

  4. 1

    h-index

  5. Animals

    1 publications · 24 citations

    1

    h-index

1–5