1 citations · 1 across the 5 of their papers we have counts for
3 papers · 1 filter
Communication-Efficient Federated Learning via Regularized Sparse Random Networks
Mohamad Mestoukirdi, Omid Esrafilian, David Gesbert +2
This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary ma…
User-Centric Federated Learning: Trading off Wireless Resources for Personalization
Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert +1
Statistical heterogeneity across clients in a Federated Learning (FL) system increases the algorithm convergence time and reduces the generalization performance, resulting in a lar…
User-Centric Federated Learning
Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert +2
Data heterogeneity across participating devices poses one of the main challenges in federated learning as it has been shown to greatly hamper its convergence time and generalizatio…