Time-varying Signals Recovery via Graph Neural Networks
- URL: http://arxiv.org/abs/2302.11313v3
- Date: Sat, 12 Aug 2023 22:47:28 GMT
- Title: Time-varying Signals Recovery via Graph Neural Networks
- Authors: Jhon A. Castro-Correa, Jhony H. Giraldo, Anindya Mondal, Mohsen
Badiey, Thierry Bouwmans, Fragkiskos D. Malliaros
- Abstract summary: 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.
- Score: 6.206392817156767
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.