Secure Domain Adaptation with Multiple Sources

Published: 18 Oct 2022, Last Modified: 28 Feb 2023Accepted by TMLREveryoneRevisionsBibTeX
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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: We have tried to address all concerns raised by the reviewers by performing new experiments and improving the presentation.
Assigned Action Editor: ~Pin-Yu_Chen1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 168