Can I read Optimal Transport for Conditional Domain Matching and Label Shift on EtoBox?

Optimal Transport for Conditional Domain Matching and Label Shift by A. Rakotomamonjy; R. Flamary; G. Gasso; M. El Alaya; M. Berar; N. Courty is a Computer Science article available to read on EtoBox.

What is Optimal Transport for Conditional Domain Matching and Label Shift about?

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 digits,VisDA and Office.

Who reads Optimal Transport for Conditional Domain Matching and Label Shift?

Author

A. Rakotomamonjy; R. Flamary; G. Gasso; M. El Alaya; M. Berar; N. Courty

Publisher

Springer Science and Business Media LLC

Published

2021

Language

EN

Field

Computer Science (Physical Sciences)