Multi-View Self-Attention for Regression Domain Adaptation with Feature Selection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Multi-View Self-Attention for Regression Domain Adaptation with Feature Selection

Résumé

In this paper, we address the problem of unsupervised domain adaptation in a regression setting considering that source data have different representations (multiple views). In this work, we investigate an original method which takes advantage of different representations using a discrepancy distance while using attention-based neural networks mechanism to estimate feature importance in domain adaptation. For this purpose, we will begin by introducing a novel formulation of the optimization objective. Then, we will develop an adversarial network domain adaptation algorithm adjusting weights given to each feature, ensuring that those related to the target receive higher weights. Finally, we will evaluate our method on public dataset and compare it to other domain adaptation baselines to demonstrate the improvement for regression tasks.
Fichier principal
Vignette du fichier
sub_315.pdf.pdf (305.97 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04230643 , version 1 (06-10-2023)

Identifiants

Citer

Mehdi Hennequin, Khalid Benabdeslem, Haytham Elghazel, Thomas Ranvier, Eric Michoux. Multi-View Self-Attention for Regression Domain Adaptation with Feature Selection. 29th International Conference on Neural Information Processing, Nov 2022, New Delhi, India. pp.177-188, ⟨10.1007/978-3-031-30105-6_15⟩. ⟨hal-04230643⟩
25 Consultations
60 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More