Secure Domain Adaptation with Multiple Sources

TL;DR

This paper introduces a secure multi-source domain adaptation method that aligns source and target distributions without sharing raw data, addressing privacy concerns in domain adaptation.

Contribution

It proposes a novel MUDA algorithm that estimates source features and predicts using confidence-based model combinations, suitable for privacy-constrained scenarios.

Findings

Effective in aligning domains without data sharing

Theoretically supported approach

Empirically outperforms existing methods

Abstract

Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains. When the source domains are distributed, data privacy and security can become significant concerns and protocols may limit data sharing, yet existing MUDA methods overlook these constraints. We develop an algorithm to address MUDA when source domain data cannot be shared with the target or across the source domains. Our method is based on aligning the distributions of source and target domains indirectly via estimating the source feature embeddings and predicting over a confidence based combination of domain specific model predictions. We provide theoretical analysis to support our approach and conduct empirical experiments to demonstrate that our algorithm is effective.