Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
This addresses forecasting problems in scientific and industrial domains where multivariate signals have intricate dependencies, representing an incremental improvement over existing graph-based methods.
The paper tackles the challenge of modeling multivariate time series with long-range dependencies and complex interactions by representing signals as nodes in a graph and using graph neural networks with attention mechanisms and hierarchical decompositions. The results show an average 23% reduction in mean squared error compared to existing models on real-world benchmark datasets.
Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions--both direct and indirect. To confront these complexities, we introduce a method of representing multivariate signals as nodes in a graph with edges indicating interdependency between them. Specifically, we leverage graph neural networks (GNN) and attention mechanisms to efficiently learn the underlying relationships within the time series data. Moreover, we suggest employing hierarchical signal decompositions running over the graphs to capture multiple spatial dependencies. The effectiveness of our proposed model is evaluated across various real-world benchmark datasets designed for long-term forecasting tasks. The results consistently showcase the superiority of our model, achieving an average 23\% reduction in mean squared error (MSE) compared to existing models.