Research Area:  Machine Learning
We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication. Our approach - drawing on ensemble learning and knowledge aggregation - achieves an average relative gain of 51.5% in AUC over local baselines and comes within 90.1% of the (unattainable) global ideal. We discuss these methods and identify several promising directions of future work.
Author(s) Name:  Neel Guha, Ameet Talwalkar, Virginia Smith
Journal name:  Computer Science
Publisher name:  arXiv:1902.11175
Paper Link:   https://arxiv.org/abs/1902.11175