Discrete Graph Structure Learning for Forecasting Multiple Time Series

Chao Shang, Jie Chen, Jinbo Bi

Keywords: Time series forecasting, graph neural network, graph structure learning

Abstract: Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.

One-sentence Summary: We propose a graph neural network approach that learns a graph structure to enhance the forecasting of multiple multivariate time series.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ chaoshangcs/GTS](https://github.com/chaoshangcs/GTS)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2101.06861/code)