no code implementations • 19 Sep 2023 • Mohamad Mestoukirdi, Omid Esrafilian, David Gesbert, Qianrui Li, Nicolas Gresset
In this setting, a binary mask is optimized instead of the model weights, which are kept fixed.
no code implementations • 25 Apr 2023 • Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert, Qianrui Li
Statistical heterogeneity across clients in a Federated Learning (FL) system increases the algorithm convergence time and reduces the generalization performance, resulting in a large communication overhead in return for a poor model.
no code implementations • 4 Jun 2022 • Mohamad Mestoukirdi, Omid Esrafilian, David Gesbert, Qianrui Li
We propose a heuristic metric as a proxy for the training performance of the different tasks.
no code implementations • 19 Oct 2021 • Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert, Qianrui Li, Nicolas Gresset
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 generalization capabilities.