Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting

TL;DR

This paper introduces a novel graph neural network approach that models dynamic, multi-scale interactions in multivariate time series, capturing evolving correlations and improving forecasting accuracy.

Contribution

It proposes a hierarchical, multi-scale graph structure combined with recurrent adjacency matrices to model evolving and scale-specific interactions in time series forecasting.

Findings

Outperforms state-of-the-art methods in forecasting accuracy.

Effectively captures dynamic and multi-scale variable interactions.

Demonstrates robustness across different forecasting tasks.

Abstract

Recent studies have shown great promise in applying graph neural networks for multivariate time series forecasting, where the interactions of time series are described as a graph structure and the variables are represented as the graph nodes. Along this line, existing methods usually assume that the graph structure (or the adjacency matrix), which determines the aggregation manner of graph neural network, is fixed either by definition or self-learning. However, the interactions of variables can be dynamic and evolutionary in real-world scenarios. Furthermore, the interactions of time series are quite different if they are observed at different time scales. To equip the graph neural network with a flexible and practical graph structure, in this paper, we investigate how to model the evolutionary and multi-scale interactions of time series. In particular, we first provide a hierarchical graph structure cooperated with the dilated convolution to capture the scale-specific correlations among time series. Then, a series of adjacency matrices are constructed under a recurrent manner to represent the evolving correlations at each layer. Moreover, a unified neural network is provided to integrate the components above to get the final prediction. In this way, we can capture the pair-wise correlations and temporal dependency simultaneously. Finally, experiments on both single-step and multi-step forecasting tasks demonstrate the superiority of our method over the state-of-the-art approaches.