Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
About
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 $\textbf{M}$ultivariate $\textbf{T}$ime series with dynamic $\textbf{G}$raph neural $\textbf{O}$rdinary $\textbf{D}$ifferential $\textbf{E}$quations ($\texttt{MTGODE}$). 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 $\texttt{MTGODE}$ from various perspectives on five time series benchmark datasets.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Traffic Forecasting | PeMS08 | -- | 181 | |
| Traffic Forecasting | PeMS03 | MAPE (Avg)14.4 | 32 | |
| Traffic Forecasting | PeMS04 | MAPE (Avg)100.1 | 32 | |
| Mortality Prediction | PhysioNet 2012 (test) | AUC74.4 | 29 | |
| Human Activity Recognition | PAMAP2 (test) | Accuracy80.3 | 28 | |
| Traffic Flow Forecasting | PeMS07 | MAPE9.3 | 25 | |
| Traffic Flow Prediction | TDrive | MAPE253.9 | 15 | |
| Traffic Flow Prediction | CHBike | MAPE102.7 | 15 | |
| Mortality Prediction | PhysioNet 2019 (test) | AUROC81.9 | 14 | |
| Traffic Flow Forecasting | NYCTaxi | Averaged MAPE76.5 | 7 |