Adversarial Weighting for Domain Adaptation in Regression

Antoine de Mathelin (1, 2) , Guillaume Richard (1, 3) , Mathilde Mougeot (1, 4) , Nicolas Vayatis (1)

1 CB - CB - Centre Borelli - UMR 9010
2 Société Michelin
3 EDF - EDF
4 ENSIIE - Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise

We present a novel instance based approach to handle regression tasks in the context of supervised domain adaptation. The approach developed in this paper relies on the assumption that the task on the target domain can be efficiently learned by adequately reweighting the source instances during training phase. We introduce a novel formulation of the optimization objective for domain adaptation which relies on a discrepancy distance characterizing the difference between domains according to a specific task and a class of hypotheses. To solve this problem, we develop an adversarial network algorithm which learns both the source weighting scheme and the task in one feed-forward gradient descent. We provide numerical evidence of the relevance of the method on public datasets for domain adaptation through reproducible experiments accessible via an online demo interface.

Domaines: Réseau de neurones [cs.NE]; Statistiques [math.ST]; Optimisation et contrôle [math.OC]

Antoine de Mathelin, Guillaume Richard, Mathilde Mougeot, Nicolas Vayatis. Adversarial Weighting for Domain Adaptation in Regression. 2021. ⟨hal-02867802v2⟩