no code implementations • 18 Mar 2024 • S. Jamal Seyedmohammadi, S. Kawa Atapour, Jamshid Abouei, Arash Mohammadi
Conventional FL, however, is susceptible to gradient inversion attacks, restrictively enforces a uniform architecture on local models, and suffers from model heterogeneity (model drift) due to non-IID local datasets.
no code implementations • 16 Feb 2024 • Kawa Atapour, S. Jamal Seyedmohammadi, Jamshid Abouei, Arash Mohammadi, Konstantinos N. Plataniotis
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework.