Private Federated Learning with Domain Adaptation

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.

Presented at the Workshop on Federated Learning for Data Privacy and Confidentiality (in Conjunction with NeurIPS 2019)

References in corpus (3)

• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Frustratingly Easy Domain Adaptation
• Towards Federated Learning at Scale: System Design

Cited by in corpus (7)

• Lower Bounds and Optimal Algorithms for Personalized Federated Learning
• Personalized Federated Learning with First Order Model Optimization
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• FedJAX: Federated learning simulation with JAX
• Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes
• Personalised Federated Learning: A Combinational Approach
• Recyclable Gaussian Processes