Multivariate Time Series Forecasting With Dynamic Graph Neural ODEs

作者：Jin, Ming; Zheng, Yu; Li, Yuan-Fang; Chen, Siheng; Yang, Bin; Pan, Shirui^*

来源：IEEE Transactions on Knowledge and Data Engineering, 2023, 35(9): 9168-9180.

DOI：10.1109/TKDE.2022.3221989

• Multivariate time series forecasting
• graph neural networks
• neural ordinary differential equations

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, they have three fundamental limitations. (i). Discrete neural architectures: Interlacing individually parameterized spatial and temporal blocks to encode rich underlying patterns leads to discontinuous latent state trajectories and higher forecasting numerical errors. (ii). High complexity: Discrete approaches complicate models with dedicated designs and redundant parameters, leading to higher computational and memory overheads. (iii). Reliance on graph priors: Relying on predefined static graph structures limits their effectiveness and practicability in real-world applications. In this paper, we address all the above limitations by proposing a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE). Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing, allowing deeper graph propagation and fine-grained temporal information aggregation to characterize stable and precise latent spatial-temporal dynamics. Our experiments demonstrate the superiorities of MTGODE from various perspectives on five time series benchmark datasets.

• 单位
  上海交通大学