English

Time-varying Signals Recovery via Graph Neural Networks

Signal Processing 2023-08-15 v3 Machine Learning Social and Information Networks

Abstract

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.

Keywords

Cite

@article{arxiv.2302.11313,
  title  = {Time-varying Signals Recovery via Graph Neural Networks},
  author = {Jhon A. Castro-Correa and Jhony H. Giraldo and Anindya Mondal and Mohsen Badiey and Thierry Bouwmans and Fragkiskos D. Malliaros},
  journal= {arXiv preprint arXiv:2302.11313},
  year   = {2023}
}

Comments

Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, Greece