no code implementations • 12 Mar 2021 • Pallika Kanani, Virendra J. Marathe, Daniel Peterson, Rave Harpaz, Steve Bright
Users can indirectly contribute to, and directly benefit from a much larger aggregate data corpus used to train the global model.
no code implementations • 13 Dec 2019 • Daniel Peterson, Pallika Kanani, Virendra J. Marathe
Federated Learning (FL) is a distributed machine learning (ML) paradigm that enables multiple parties to jointly re-train a shared model without sharing their data with any other parties, offering advantages in both scale and privacy.
no code implementations • LREC 2014 • Daniel Peterson, Martha Palmer, Shumin Wu
We show that the least probable sentences provide dramatic improved system performance over the baseline, especially when only a small portion of the data is annotated.