MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting

TL;DR

This paper introduces MTHetGNN, a novel heterogeneous graph neural network framework that models complex static and dynamic relations among variables for improved multivariate time series forecasting.

Contribution

It presents an end-to-end deep learning model combining relation and temporal embeddings with heterogeneous graph structures, addressing complex variable relations in MTS forecasting.

Findings

MTHetGNN achieves state-of-the-art results on three real-world datasets.

The relation embedding module effectively captures diverse variable relationships.

The model outperforms existing methods in multivariate time series forecasting.

Abstract

Multivariate time series forecasting, which analyzes historical time series to predict future trends, can effectively help decision-making. Complex relations among variables in MTS, including static, dynamic, predictable, and latent relations, have made it possible to mining more features of MTS. Modeling complex relations are not only essential in characterizing latent dependency as well as modeling temporal dependence but also brings great challenges in the MTS forecasting task. However, existing methods mainly focus on modeling certain relations among MTS variables. In this paper, we propose a novel end-to-end deep learning model, termed Multivariate Time Series Forecasting via Heterogeneous Graph Neural Networks (MTHetGNN). To characterize complex relations among variables, a relation embedding module is designed in MTHetGNN, where each variable is regarded as a graph node, and each type of edge represents a specific static or dynamic relationship. Meanwhile, a temporal embedding module is introduced for time series features extraction, where involving convolutional neural network (CNN) filters with different perception scales. Finally, a heterogeneous graph embedding module is adopted to handle the complex structural information generated by the two modules. Three benchmark datasets from the real world are used to evaluate the proposed MTHetGNN. The comprehensive experiments show that MTHetGNN achieves state-of-the-art results in the MTS forecasting task.