From theoretical to practical transfer learning: the ADAPT library - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2022

From theoretical to practical transfer learning: the ADAPT library

Francois Deheeger
  • Fonction : Auteur
  • PersonId : 1370320
Mathilde Mougeot
  • Fonction : Auteur
  • PersonId : 1370321
Nicolas Vayatis
  • Fonction : Auteur
  • PersonId : 1134689

Résumé

In traditional machine learning, the learner assumes that the training and testing datasets are drawn according to the same distribution. However, in most practical scenarios, the two datasets are drawn according to two different distributions, the source distribution and the target distribution. In this context, the use of classical machine learning algorithms often fails as models trained on the source data provide poor performances on the target data. To solve this problem, many transfer learning techniques have been developed following one of the three main strategies: parameter-based transfer, instance-based transfer and feature-based transfer. The choice of the appropriate strategy is mainly determined by the nature of the shift between the source and target distributions. For example, to deal with the problem of sampling bias, when part of the population is over- or under-represented in the training set, instance-based approaches are useful to adequately reweight the source data in the training phase. If the shift is caused by a change in data acquisition, such as sensor drift, feature-based methods help to correct the shift by learning a common feature representation for the source and target data. For a real application, it is really a challenge to choose in advance the best transfer learning strategy and one often needs to evaluate different models in practice. As the different transfer methods were introduced by various contributors, no common framework is today available for a rapid development. To tackle this issue, we propose a Python library for transfer learning: ADAPT (Awesome Domain Adaptation Python Toolbox), which allows practitioners to compare the results of many methods on their particular problem.
Fichier principal
Vignette du fichier
adapt_hal.pdf (3.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04529706 , version 1 (02-04-2024)

Identifiants

Citer

Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis. From theoretical to practical transfer learning: the ADAPT library. Roozbeh Razavi-Far; Boyu Wang; Matthew E. Taylor; Qiang Yang. Federated and Transfer Learning, 27, Springer International Publishing, pp.283-306, 2022, Adaptation, Learning, and Optimization, ⟨10.1007/978-3-031-11748-0_12⟩. ⟨hal-04529706⟩
3 Consultations
3 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More