Robust Aggregation

Robust Aggregation is an aggregation mechanism in federated learning that belongs to the class of distributed averaging techniques and is specifically designed to withstand the influence of outliers, adversarial updates, or data heterogeneity by selectively weighting or filtering client contributions during model synchronization.

141

Publications

9.3K

Citations

512

Authors

213

Institutions

Publications per year

2017–2026

98

Authors

512

  1. QL
    Qing Ling

    University of Science and Technology of China, China

    6 publications · 687 citations

    6

    h-index

  2. TC
    Tianyi Chen

    University of Minnesota, United States

    5 publications · 665 citations

    5

    h-index

  3. GB
    Georgios B. Giannakis

    University of Minnesota, United States

    4 publications · 612 citations

    4

    h-index

  4. IG
    Indranil Gupta

    University of Illinois Urbana-Champaign, United States

    4 publications · 318 citations

    4

    h-index

  5. CX
    Cong Xie

    University of Jinan, China

    4 publications · 318 citations

    4

    h-index

1–5 of 512

Venues

  1. arXiv (Cornell University)

    Repository · 28 publications · 1.5K citations

    19

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 562 citations

    5

    h-index

  3. Infoscience (Ecole Polytechnique Fédérale de Lausanne)

    Repository · 5 publications · 191 citations

    5

    h-index

  4. IEEE Transactions on Signal Processing

    4 publications · 374 citations

    4

    h-index

  5. IEEE Internet of Things Journal

    4 publications · 167 citations

    4

    h-index

1–5