Time-varying Signals Recovery via Graph Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Time-varying Signals Recovery via Graph Neural Networks

Résumé

The recovery of time-varying graph signals is a fundamental problem with numerous applications in sensor networks and forecasting in time series. Effectively capturing the spatio-temporal information in these signals is essential for the downstream tasks. Previous studies have used the smoothness of the temporal differences of such graph signals as an initial assumption. Nevertheless, this smoothness assumption could result in a degradation of performance in the corresponding application when the prior does not hold. In this work, we relax the requirement of this hypothesis by including a learning module. We propose a Time Graph Neural Network (TimeGNN) for the recovery of time-varying graph signals. Our algorithm uses an encoder-decoder architecture with a specialized loss composed of a mean squared error function and a Sobolev smoothness operator.TimeGNN shows competitive performance against previous methods in real datasets.
Fichier principal
Vignette du fichier
2302.11313 (4).pdf (1.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04368767 , version 1 (01-01-2024)

Identifiants

Citer

John A Castro-Correa, Jhony H Giraldo, Anindya Mondal, Mohsen Badiey, Thierry Bouwmans, et al.. Time-varying Signals Recovery via Graph Neural Networks. ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096168⟩. ⟨hal-04368767⟩
45 Consultations
9 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More