Title:	federated frank-wolfe
DNr:	Berzelius-2023-106
Project Type:	LiU Berzelius
Principal Investigator:	Ali Dadras <ali.dadras@umu.se>
Affiliation:	Umeå universitet
Duration:	2023-04-21 – 2023-11-01
Classification:	10199
Homepage:	https://www.umu.se/personal/ali-dadras/
Keywords:

Abstract

Federated learning (FL) has gained much attention in recent years for building privacy- preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still very limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FEDFW). FEDFW provably finds an ε-suboptimal solution of the constrained empirical risk-minimization problem after O(ε^(−2)) iterations if the objective function is convex. The rate becomes O(ε^(−3)) if the objective is non-convex. The method enjoys data privacy, low per-iteration cost, and communication of sparse signals. We demonstrate the empirical performance of the proposed method on several machine learning tasks.