Optimal Transport for Conditional Domain Matching and Label Shift

TL;DR

This paper introduces a novel method for unsupervised domain adaptation under joint class-conditional and label shifts, leveraging optimal transport and importance weighting to align distributions and improve generalization.

Contribution

It proposes a new learning framework that combines importance weighted loss with Wasserstein distance for better domain matching under label shift, with theoretical guarantees.

Findings

Outperforms existing methods on digits, VisDA, and Office datasets.

Provides a theoretically sound estimator for target label proportions.

Demonstrates improved domain adaptation performance across multiple benchmarks.

Abstract

We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretically show that, for good generalization, it is necessary to learn a latent representation in which both marginals and class-conditional distributions are aligned across domains. For this sake, we propose a learning problem that minimizes importance weighted loss in the source domain and a Wasserstein distance between weighted marginals. For a proper weighting, we provide an estimator of target label proportion by blending mixture estimation and optimal matching by optimal transport. This estimation comes with theoretical guarantees of correctness under mild assumptions. Our experimental results show that our method performs better on average than competitors across a range domain adaptation problems including \emph{digits},\emph{VisDA} and \emph{Office}. Code for this paper is available at \url{https://github.com/arakotom/mars_domain_adaptation}.