Adversarial Multi-View Domain Adaptation for Regression - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Adversarial Multi-View Domain Adaptation for Regression

Résumé

In this paper, we address the problem of domain adaptation in a regression setting, where only a few labeled samples are available in the source domain, and no labeled samples in the target domain. In addition, we consider that source data have different representations (multiple views). In this work, we investigate an original method to take advantage of different representations using a weighted combination of views. Besides, we use a co-training approach to include information from unlabeled instances by ensuring that models trained on different views make similar predictions. For this purpose, we introduce a novel formulation of the optimization objective for domain adaptation that relies on a discrepancy distance. Then, we develop an adversarial network domain adaptation algorithm adjusting weights given to each view, ensuring that those related to the target receive higher weights. Finally, we evaluate our method on different public datasets and compare it to other domain adaptation baselines to demonstrate the improvement for regression tasks.
Fichier principal
Vignette du fichier
Adversarial_Multi_View_Domain_Adaptation_for_Regression.pdf (225.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04382606 , version 1 (09-01-2024)

Identifiants

Citer

Mehdi Hennequin, Khalid Benabdeslem, Haytham Elghazel. Adversarial Multi-View Domain Adaptation for Regression. 2022 International Joint Conference on Neural Networks (IJCNN), Jul 2022, Padoue, Italy. ⟨10.1109/IJCNN55064.2022.9892148⟩. ⟨hal-04382606⟩
9 Consultations
22 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More