Skip to main content

Time-varying Signals Recovery via Graph Neural Networks

Jhon A Castro Correa (University of Delaware); Jhony H. Giraldo (Télécom Paris); Anindya Mondal (Jadavpur University); Mohsen Badiey (University of Delaware); Thierry BOUWMANS (Univ. La Rochelle); Fragkiskos Malliaros (CentraleSupelec)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
07 Jun 2023

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.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00