Private Federated Learning with Domain Adaptation
Machine Learning
2019-12-17 v1 Cryptography and Security
Machine Learning
Abstract
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. We propose a framework to augment this collaborative model-building with per-user domain adaptation. We show that this technique improves model accuracy for all users, using both real and synthetic data, and that this improvement is much more pronounced when differential privacy bounds are imposed on the FL model.
Cite
@article{arxiv.1912.06733,
title = {Private Federated Learning with Domain Adaptation},
author = {Daniel Peterson and Pallika Kanani and Virendra J. Marathe},
journal= {arXiv preprint arXiv:1912.06733},
year = {2019}
}
Comments
Presented at the Workshop on Federated Learning for Data Privacy and Confidentiality (in Conjunction with NeurIPS 2019)