Time-varying Signals Recovery via Graph Neural Networks

TL;DR

This paper introduces TimeGNN, a novel graph neural network model that effectively recovers time-varying signals on graphs by incorporating a learning module and a specialized loss, outperforming previous methods.

Contribution

The paper proposes a new TimeGNN model that relaxes smoothness assumptions and improves recovery of time-varying graph signals using an encoder-decoder architecture with a Sobolev smoothness loss.

Findings

TimeGNN achieves competitive results on real datasets.

The model effectively captures spatio-temporal information.

Relaxing smoothness assumptions enhances performance.

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.