Communication Dans Un Congrès Année : 2025

Deep Joint Distribution Optimal Transport for Universal Domain Adaptation on Time Series

Romain Mussard
  • Fonction : Auteur
  • PersonId : 1531630
Fannia Pacheco
Maxime Berar
Gilles Gasso
Paul Honeine

Résumé

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, even when their classes are not fully shared. Few dedicated UniDA methods exist for Time Series (TS), which remains a challenging case. In general, UniDA approaches align common class samples and detect unknown target samples from emerging classes. Such detection often results from thresholding a discriminability metric. The threshold value is typically either a fine-tuned hyperparameter or a fixed value, which limits the ability of the model to adapt to new data. Furthermore, discriminability metrics exhibit overconfidence for unknown samples, leading to misclassifications. This paper introduces UniJDOT, an optimal-transport-based method that accounts for the unknown target samples in the transport cost. Our method also proposes a joint decision space to improve the discriminability of the detection module. In addition, we use an auto-thresholding algorithm to reduce the dependence on fixed or fine-tuned thresholds. Finally, we rely on a Fourier transform-based layer inspired by the Fourier Neural Operator for better TS representation. Experiments on TS benchmarks demonstrate the discriminability, robustness, and state-of-the-art performance of UniJDOT.

Fichier principal
Vignette du fichier
UniJDOT_CC4.pdf (1.77 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05031338 , version 1 (11-04-2025)

Licence

Identifiants

Citer

Romain Mussard, Fannia Pacheco, Maxime Berar, Gilles Gasso, Paul Honeine. Deep Joint Distribution Optimal Transport for Universal Domain Adaptation on Time Series. 2025 International Joint Conference on Neural Networks (IJCNN), Jun 2025, Rome, Italy. ⟨10.1109/IJCNN64981.2025.11229152⟩. ⟨hal-05031338⟩
119 Consultations
151 Téléchargements

Altmetric

Partager

  • More