Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

by   Ming Jin, et al.

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 suffer from 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.


page 1

page 2

page 3

page 4


Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting

Multivariate Time Series (MTS) forecasting plays a vital role in a wide ...

Learning Structured Components: Towards Modular and Interpretable Multivariate Time Series Forecasting

Multivariate time-series (MTS) forecasting is a paramount and fundamenta...

Nexus sine qua non: Essentially connected neural networks for spatial-temporal forecasting of multivariate time series

Modeling and forecasting multivariate time series not only facilitates t...

Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting

Multivariate Time Series (MTS) forecasting plays a vital role in a wide ...

Multivariate Time Series Regression with Graph Neural Networks

Machine learning, with its advances in Deep Learning has shown great pot...

A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields

Self-awareness is the key capability of autonomous systems, e.g., autono...

Long-Range Transformers for Dynamic Spatiotemporal Forecasting

Multivariate Time Series Forecasting (TSF) focuses on the prediction of ...

Please sign up or login with your details

Forgot password? Click here to reset