Model Aggregation

Model Aggregation is a computational process in federated learning that combines locally updated model parameters from distributed clients into a single global model update, distinguishing itself from centralized training methods by preserving data locality and enabling collaborative learning without direct data sharing.

894

Publications

61.3K

Citations

2.7K

Authors

765

Institutions

Publications per year

2017–2026

802

Authors

2.7K

  1. YS
    Yuanming Shi

    ShanghaiTech University, China

    14 publications · 1.8K citations

    15

    h-index

  2. HV
    H. Vincent Poor

    Princeton University, United States

    15 publications · 3.4K citations

    14

    h-index

  3. TQ
    Tony Q. S. Quek

    Singapore University of Technology and Design, Singapore

    12 publications · 3.2K citations

    13

    h-index

  4. YZ
    Yong Zhou

    ShanghaiTech University, China

    10 publications · 512 citations

    13

    h-index

  5. DN
    Dusit Niyato

    Nanyang Technological University, Singapore

    9 publications · 746 citations

    11

    h-index

1–5 of 2.7K

Venues

  1. arXiv (Cornell University)

    Repository · 100 publications · 13.2K citations

    35

    h-index

  2. IEEE Internet of Things Journal

    33 publications · 1.8K citations

    24

    h-index

  3. IEEE Transactions on Wireless Communications

    24 publications · 2.7K citations

    23

    h-index

  4. IEEE Transactions on Mobile Computing

    TMCCI · 12 publications · 706 citations

    16

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 1.8K citations

    15

    h-index

1–5