Time-varying Signals Recovery via Graph Neural 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.

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

References in corpus (10)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Graph Transformer Networks
• Sampling of graph signals with successive local aggregations
• Kernel-based Reconstruction of Graph Signals
• Reconstruction of Time-varying Graph Signals via Sobolev Smoothness
• A Hilbert Space Theory of Generalized Graph Signal Processing
• Higher-order Clustering and Pooling for Graph Neural Networks
• Graph Vertex Sampling with Arbitrary Graph Signal Hilbert Spaces
• Recovery of Missing Sensor Data by Reconstructing Time-varying Graph Signals

Cited by in corpus (2)

• Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
• Scaling Methods To Estimate Macroscopic Fundamental Diagrams in Urban Networks with Sparse Sensor Coverage