Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series

2022/03/08 by Wang, Yuanrong, Aste, Tomaso
#Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2203.03991

Abstract

We propose an end-to-end architecture for multivariate time-series prediction that integrates a spatial-temporal graph neural network with a matrix filtering module. This module generates filtered (inverse) correlation graphs from multivariate time series before inputting them into a GNN. In contrast with existing sparsification methods adopted in graph neural network, our model explicitly leverage time-series filtering to overcome the low signal-to-noise ratio typical of complex systems data. We present a set of experiments, where we predict future sales from a synthetic time-series sales dataset. The proposed spatial-temporal graph neural network displays superior performances with respect to baseline approaches, with no graphical information, and with fully connected, disconnected graphs and unfiltered graphs.

Related

• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
• TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
• A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification