Timezone: »

 
Poster
Federated Multi-Task Learning
Virginia Smith · Chao-Kai Chiang · Maziar Sanjabi · Ameet S Talwalkar

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #74
in Posters Mon »

Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In this work, we show that multi-task learning is naturally suited to handle the statistical challenges of this setting, and propose a novel systems-aware optimization method, MOCHA, that is robust to practical systems issues. Our method and theory for the first time consider issues of high communication cost, stragglers, and fault tolerance for distributed multi-task learning. The resulting method achieves significant speedups compared to alternatives in the federated setting, as we demonstrate through simulations on real-world federated datasets.

Keywords: Convex Optimization · Multitask and Transfer Learning · Hardware and Systems
[ Code]  [ Paper] 

Author Information

Virginia Smith (Stanford University)
Chao-Kai Chiang (University of Southern California)
Maziar Sanjabi (University of Southern California)
Ameet S Talwalkar (CMU)

More from the Same Authors