federated frank-wolfe
Title: federated frank-wolfe
DNr: Berzelius-2024-36
Project Type: LiU Berzelius
Principal Investigator: Ali Dadras <ali.dadras@umu.se>
Affiliation: Umeå universitet
Duration: 2024-03-15 – 2024-10-01
Classification: 10199
Homepage: https://www.umu.se/personal/ali-dadras/


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.