QR kód

Slingshot: Globally Favorable Local Updates for Federated Learning

Federated Learning (FL), as a promising distributed learning paradigm, is proposed to solve the contradiction between the data hunger of modern machine learning and the increasingly stringent need for data privacy. However, clients naturally present different distributions of their local data and in...

Celý popis

Uloženo v:
Hlavní autoři: Jialiang Liu, Huawei Huang, Chun Wang, Sicong Zhou, Ruixin Li, Zibin Zheng
Médium: Artigo
Jazyk:Inglês
Vydáno: IEEE 2024-01-01
Edice:IEEE Open Journal of the Computer Society
Témata:
Federated learning
data heterogeneity
catastrophic forgetting
model performance
On-line přístup:https://ieeexplore.ieee.org/document/10411043/
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky