Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Match and Reweight Strategy for Generalized Target Shift

Alain Rakotomamonjy 1, 2 Rémi Flamary 3 Gilles Gasso 1 Mokhtar Alaya Maxime Berar 1 Nicolas Courty 4
1 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
4 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : We address the problem of unsupervised domain adaptation under the setting of generalized target shift (both class-conditional and label shifts occur). We show that in that setting, for good generalization, it is necessary to learn with similar source and target label distributions and to match the class-conditional probabilities. For this purpose, we propose an estimation of target label proportion by blending mixture estimation and optimal transport. This estimation comes with theoretical guarantees of correctness. Based on the estimation, we learn a model by minimizing a importance weighted loss and a Wasserstein distance between weighted marginals. We prove that this minimization allows to match class-conditionals given mild assumptions on their geometry. Our experimental results show that our method performs better on average than competitors accross a range domain adaptation problems including digits,VisDA and Office.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02866979
Contributor : Alain Rakotomamonjy <>
Submitted on : Thursday, October 15, 2020 - 4:03:03 PM
Last modification on : Sunday, October 18, 2020 - 3:30:21 AM

Files

dann_targetshift_arxiv.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02866979, version 2

Citation

Alain Rakotomamonjy, Rémi Flamary, Gilles Gasso, Mokhtar Alaya, Maxime Berar, et al.. Match and Reweight Strategy for Generalized Target Shift. 2020. ⟨hal-02866979v2⟩

Share

Metrics

Record views

43

Files downloads

26