Private Federated Learning with Domain Adaptation

TL;DR

This paper introduces a federated learning framework enhanced with domain adaptation, significantly improving model accuracy for individual users, especially under privacy constraints, demonstrated through experiments with real and synthetic data.

Contribution

The paper presents a novel integration of domain adaptation into federated learning, enhancing personalization and accuracy under privacy-preserving conditions.

Findings

Model accuracy improves with domain adaptation in FL.

Privacy bounds amplify the benefits of domain adaptation.

Results validated on real and synthetic datasets.

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.