Domain Generalization by Marginal Transfer Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Machine Learning Research Year : 2021

Domain Generalization by Marginal Transfer Learning

Abstract

In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This problem arises in several applications where data distributions fluctuate because of environmental, technical, or other sources of variation. We introduce a formal framework for DG, and argue that it can be viewed as a kind of supervised learning problem by augmenting the original feature space with the marginal distribution of feature vectors. While our framework has several connections to conventional analysis of supervised learning algorithms, several unique aspects of DG require new methods of analysis. This work lays the learning theoretic foundations of domain generalization, building on our earlier conference paper where the problem of DG was introduced Blanchard et al., 2011. We present two formal models of data generation, corresponding notions of risk, and distribution-free generalization error analysis. By focusing our attention on kernel methods, we also provide more quantitative results and a universally consistent algorithm. An efficient implementation is provided for this algorithm, which is experimentally compared to a pooling strategy on one synthetic and three real-world data sets.
Fichier principal
Vignette du fichier
17-679.pdf (1.08 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-02974216 , version 1 (25-08-2021)

Licence

Attribution

Identifiers

Cite

Gilles Blanchard, Aniket Anand Deshmukh, Urun Dogan, Gyemin Lee, Clayton Scott. Domain Generalization by Marginal Transfer Learning. Journal of Machine Learning Research, 2021, 22 (2), pp.1-55. ⟨hal-02974216⟩
128 View
79 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More