Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment

Résumé

While large volumes of unlabeled data are usually available, associated labels are often scarce. The unsupervised domain adaptation problem aims at exploiting labels from a source domain to classify data from a related, yet different, target domain. When time series are at stake, new difficulties arise as temporal shifts may appear in addition to the standard feature distribution shift. In this paper, we introduce the Match-And-Deform (MAD) approach that aims at finding correspondences between the source and target time series while allowing temporal distortions. The associated optimization problem simultaneously aligns the series thanks to an optimal transport loss and the time stamps through dynamic time warping. When embedded into a deep neural network, MAD helps learning new representations of time series that both align the domains and maximize the discriminative power of the network. Empirical studies on benchmark datasets and remote sensing data demonstrate that MAD makes meaningful sample-to-sample pairing and time shift estimation, reaching similar or better classification performance than state-of-the-art deep time series domain adaptation strategies.

Dates et versions

hal-04189149 , version 1 (28-08-2023)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

François Painblanc, Laetitia Chapel, Nicolas Courty, Chloé Friguet, Charlotte Pelletier, et al.. Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment. ECML PKDD 2023, Sep 2023, Torino, Italy. ⟨hal-04189149⟩
44 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More