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

Mapping conditional distributions for domain adaptation under generalized target shift

Abstract : We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unlike simpler UDA settings, few works have addressed this challenging problem. Recent approaches learn domain-invariant representations, yet they have practical limitations and rely on strong assumptions that may not hold in practice. In this paper, we explore a novel and general approach to align pretrained representations, which circumvents existing drawbacks. Instead of constraining representation invariance, it learns an optimal transport map, implemented as a NN, which maps source representations onto target ones. Our approach is flexible and scalable, it preserves the problem's structure and it has strong theoretical guarantees under mild assumptions. In particular, our solution is unique, matches conditional distributions across domains, recovers target proportions and explicitly controls the target generalization risk. Through an exhaustive comparison on several datasets, we challenge the state-of-the-art in GeTarS.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Matthieu Kirchmeyer Connect in order to contact the contributor
Submitted on : Monday, October 25, 2021 - 10:39:31 AM
Last modification on : Tuesday, November 16, 2021 - 4:03:03 AM


Files produced by the author(s)


  • HAL Id : hal-03396183, version 1
  • ARXIV : 2110.15057


Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac, Patrick Gallinari. Mapping conditional distributions for domain adaptation under generalized target shift. 2021. ⟨hal-03396183⟩



Record views


Files downloads