Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

TL;DR

This paper introduces a novel graph neural network framework for multivariate time series forecasting that automatically learns spatial dependencies and captures complex temporal patterns, outperforming existing methods on benchmark datasets.

Contribution

It proposes a general GNN-based framework with automatic relation learning, a mix-hop propagation layer, and a dilated inception layer for improved multivariate time series forecasting.

Findings

Outperforms state-of-the-art methods on 3 of 4 benchmark datasets

Achieves comparable performance on traffic datasets with structural information

Demonstrates effective automatic learning of variable relations

Abstract

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.