Description
Date depot: 12 avril 2023
Titre: Peer-to-peer Cybersecure Federated Learning
Directrice de thèse:
Maria POTOP-BUTUCARU (LIP6)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Systèmes et réseaux
Resumé: The ambition of the thesis is to enhance the concept of FML (Federated Machine Learning) and MADRL (Multi-agent deep reinforcement learning) to a new concept of peer-to-peer CF-DRL (CyberSecure Distributed Reinforced Learning). Follow the FML principles, peer-to-peer CF-DRL will utilize local data for model training and aggregated iteratively via peer-to-peer exchanges. However, since FML is associated with frequent information exchange and communication overheads, the thesis will propose and evaluate the effectiveness of different optimization methods.
Doctorant.e: Pham Alexandre