Aurélien Bellet, a “Directeur de Recherche” at Inria, leader in the field of Federated Learning is joining PreMeDiCal at the begining of August 2023. The team is extremely pleased to welcome him. Besides Federated Learning, Aurélien also works on privacy and fairness in machine learning, and more generally optimization for ML, graph-based ML and recently health applications.
Aurelien is the co-author of a reference survey published in the prestigious journal Foundations and Trends in Machine Learning [1], and has created an online seminar with worldwide audience. He has also initiated collaborative projects with several hospitals in the north of France (including Lille University Hospital) to deploy federated learning for conducting multi-centric medical studies without centralizing data. This ongoing project involves some open-source software development [2], a study of the regulatory requirements with the help of CNIL, and deployments in hospitals on concrete-uses like re-hospitalization prediction and diagnostic coding from medical text reports.
[1] Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., et al. “Advances and Open Problems in Federated Learning”. Foundations and Trends® in Machine Learning 14:1–2, pp. 1–210.
[2] See Declearn and Fed-BioMed.
