Learning Dynamic Temporal Relations with Continuous Graph for Multivariate Time Series Forecasting (Student Abstract)
DOI:
https://doi.org/10.1609/aaai.v37i13.27039Keywords:
Graph Neural Network, Multivariate Time Series Forecasting, Neural Differential Equation, Continuous InferenceAbstract
The recent advance in graph neural networks (GNNs) has inspired a few studies to leverage the dependencies of variables for time series prediction. Despite the promising results, existing GNN-based models cannot capture the global dynamic relations between variables owing to the inherent limitation of their graph learning module. Besides, multi-scale temporal information is usually ignored or simply concatenated in prior methods, resulting in inaccurate predictions. To overcome these limitations, we present CGMF, a Continuous Graph learning method for Multivariate time series Forecasting (CGMF). Our CGMF consists of a continuous graph module incorporating differential equations to capture the long-range intra- and inter-relations of the temporal embedding sequence. We also introduce a controlled differential equation-based fusion mechanism that efficiently exploits multi-scale representations to form continuous evolutional dynamics and learn rich relations and patterns shared across different scales. Comprehensive experiments demonstrate the effectiveness of our method for a variety of datasets.Downloads
Published
2024-07-15
How to Cite
Wang, Z., Zhou, F., Trajcevski, G., Zhang, K., & Zhong, T. (2024). Learning Dynamic Temporal Relations with Continuous Graph for Multivariate Time Series Forecasting (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16358-16359. https://doi.org/10.1609/aaai.v37i13.27039
Issue
Section
AAAI Student Abstract and Poster Program