Retour aux activités
Séminaire d'apprentissage automatique efficace

Federated learning meets multi-objective optimization

iCalendar

12 fév. 2021   13h00 — 14h00

Kiarash Shaloudegi Huawei Noah’s Ark, Canada

Kiarash Shaloudegi

Présentation sur YouTube

Federated learning has emerged as a promising, massively distributed way to train a joint deep model over large amounts of edge devices while keeping private user data strictly on device. In this work, motivated from ensuring fairness among users and robustness against malicious adversaries, we formulate federated learning as multi-objective optimization and propose a new algorithm FedMGDA+ that is guaranteed to converge to Pareto stationary solutions. FedMGDA+ is simple to implement, has fewer hyperparameters to tune, and refrains from sacrificing the performance of any participating user. We establish the convergence properties of FedMGDA+ and point out its connections to existing approaches. Extensive experiments on a variety of datasets confirm that FedMGDA+ compares favorably against state-of-the-art.


Inscrivez-vous à la notification par e-mail des séminaires d'apprentissage automatique efficace du GERAD.

Vahid Partovi Nia responsable

Lieu

Webinaire
Zoom
Montréal Québec
Canada