[PDF] nsf.gov

[PDF][PDF] Diverse client selection for federated learning via submodular maximization

International Conference on Learning Representations, 2022 - par.nsf.gov
In every communication round of federated learning, a random subset of clients
communicate their model updates back to the server which then aggregates them all. The …
被引用次数：91 相关文章

[引用][C] DIVERSE CLIENT SELECTION FOR FEDERATED LEARNING VIA SUBMODULAR MAXIMIZATION

R Balakrishnan, J Bilmes - Genome Biology, 2023 - Elsevier
[PDF] nsf.gov

[PDF][PDF] Diverse client selection for federated learning via submodular maximization

R Balakrishnan, T Li, T Zhou, N Himayat… - International …, 2022 - par.nsf.gov
In every communication round of federated learning, a random subset of clients
communicate their model updates back to the server which then aggregates them all. The …

Diverse Client Selection for Federated Learning via Submodular Maximization

R Balakrishnan, T Li, T Zhou, N Himayat… - … Conference on Learning … - openreview.net
In every communication round of federated learning, a random subset of clients
communicate their model updates back to the server which then aggregates them all. The …