One-Shot Federated Learning

• DOI: 10.48550/arxiv.1902.11175
• Publication Date: 2019-01-01
• Authors: Guha, Neel; Talwalkar, Ameet; Smith, Virginia
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Statistics - Machine Learning; 0202 electrical engineering, electronic engineering, information engineering; Machine Learning (stat.ML); 02 engineering and technology; Machine Learning (cs.LG)

5 pages, 3 figures, 1 table. 2nd Workshop on Machine Learning on the Phone and other Consumer Devices, NeurIPs 2018<br/>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.<br/>