Heterogeneous Federated Learning via Personalized Generative Networks

no code implementations • 25 Aug 2023 • Zahra Taghiyarrenani, Abdallah Alabdallah, Slawomir Nowaczyk, Sepideh Pashami

In this paper, we provide theoretical proof that minimizing heterogeneity between clients facilitates the convergence of a global model for every single client.

Federated Learning Transfer Learning