Description
Date depot: 3 janvier 2023
Titre: Improvement of Federated Learning Models for E-health
Directeur de thèse:
Jean-Francois PRADAT-PEYRE (LIP6)
Directeur de thèse:
Abbass NASSER (American University of Culture & Education (AUCE))
Directeur de thèse:
Jean-Francois PRADAT-PEYRE (LIP6)
Directeur de thèse:
Abbass NASSER (American University of Culture & Education (AUCE))
Encadrante :
Sonia SAADAOUI (LAMSADE)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Systèmes et architectures intégrés matériel-logiciel
Resumé: Federated Learning (FL) has been used in many fields, from medicine to the Internet of Things (IoT), transportation, defense, and mobile apps. Furthermore, FL has recently been proposed for building intelligent and privacy enhanced IoT systems penetrating many facets of our daily lives with the proliferation of intelligent services and applications empowered by artificial intelligence (AI). However, many challenges remain to obtain an efficient and well accepted solution.
The objectives of this DRP are twofold:
first determine how to develop FL algorithms with different local machine learning methods and possible data and system heterogeneity to federate the largest number of institutions working on a given disease.
second design an adaptive FL system that handles various sets of metrics such as sparsification, robustness, quantification, scalability, security, and privacy, which will be implemented in specific IoT domains (e.g., e-health) while considering the capacity of IoT systems.
Doctorant.e: Salman Hassan