Aurélien Bellet (Researcher, Inria) will run a Seminar@SystemX online on the following topic “Introduction to Federated Learning”, on May 19, from 2:00 pm to 3:30 pm.
This event is organized in collaboration with DATAIA Paris-Saclay institute.
Link to connect to the webinar.
Resume :
Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model while keeping their data decentralized. FL embodies the principles of focused data collection and minimization and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. In this talk, Aurélien Bellet will introduce various settings that fall under the umbrella of FL, review a few standard algorithms, and discuss some recent work and open problems related to dealing with heterogeneous datasets and preserving privacy.
Biography :
Aurélien Bellet is a researcher at Inria. He obtained his Ph.D from the University of Saint-Etienne (France) in 2012 and was a postdoctoral researcher at the University of Southern California (USA) and at Télécom Paris (France). His current research focuses on the design of federated and decentralized machine learning algorithms under privacy constraints. Aurélien served as area chair for ICML 2019, ICML
2020 and NeurIPS 2020 and co-organized several international workshops on machine learning and privacy (at NIPS 2016, NeurIPS 2018 and NeurIPS 2020, and as stand-alone events). He is also co-organizer of the FLOW seminar, which provides a global online forum for the dissemination of the latest scientific research results in all aspects of federated learning.