Multi-scale temporal features extraction based graph convolutional network with attention for multivariate time series prediction

Modeling for multivariate time series have always been a meaningful subject. Multivariate time series forecasting is a fundamental problem attracting many researchers in various fields. However, most of the existing methods focused on univariate prediction and rarely take into account the potential spatial dependencies between mul-tiple variables. Multivariate time series forecasting can be naturally viewed from graph perspective, where each variable from multivariate time series can be viewed as a node in the graph, and they are interlinked through hidden dependencies. Therefore, a novel graph neural network model based on multi-scale temporal feature extraction and attention mechanism is proposed for multivariate time series prediction. Specifically, empirical modal decomposition is used to extract the time-domain features of multivariate time series at different time scales to form the node features of the graph. Meanwhile, the multi-head attention mechanism is applied to construct potential associations between nodes and enhance the rationality of relationships in the graph. Furthermore, the graph convolutional neural network is used to generate node embeddings that contain rich spatial relationships. Finally, the temporal convolutional network establishes temporal relationships for the node embedding to achieve multivariate time series prediction. The real data from the financial, traffic and medical fields confirm the effectiveness of the proposed model.

Automated summary

This paper proposes a novel graph neural network model for multivariate time series prediction. The model extracts time-domain features at different time scales using empirical modal decomposition, constructs associations between nodes using multi-head attention mechanism and graph convolutional neural network, and achieves accurate prediction for multivariate time series.