TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
This work addresses scalability and efficiency issues in time series forecasting for real-world applications, representing an incremental improvement over existing graph-based methods.
The paper tackles the problem of costly and unscalable training in graph neural network approaches for multivariate time series forecasting by proposing TimeGNN, which learns dynamic temporal graph representations to capture evolving inter-series patterns and correlations, achieving inference times 4 to 80 times faster than other state-of-the-art graph-based methods with comparable forecasting performance.
Time series forecasting lies at the core of important real-world applications in many fields of science and engineering. The abundance of large time series datasets that consist of complex patterns and long-term dependencies has led to the development of various neural network architectures. Graph neural network approaches, which jointly learn a graph structure based on the correlation of raw values of multivariate time series while forecasting, have recently seen great success. However, such solutions are often costly to train and difficult to scale. In this paper, we propose TimeGNN, a method that learns dynamic temporal graph representations that can capture the evolution of inter-series patterns along with the correlations of multiple series. TimeGNN achieves inference times 4 to 80 times faster than other state-of-the-art graph-based methods while achieving comparable forecasting performance