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

by   Tong Nie, et al.

Modeling and forecasting multivariate time series not only facilitates the decision making of practitioners, but also deepens our scientific understanding of the underlying dynamical systems. Spatial-temporal graph neural networks (STGNNs) are emerged as powerful predictors and have become the de facto models for learning spatiotemporal representations in recent years. However, existing architectures of STGNNs tend to be complicated by stacking a series of fancy layers. The designed models could be either redundant or enigmatic, which pose great challenges on their complexity and scalability. Such concerns prompt us to re-examine the designs of modern STGNNs and identify core principles that contribute to a powerful and efficient neural predictor. Here we present a compact predictive model that is fully defined by a dense encoder-decoder and a message-passing layer, powered by node identifications, without any complex sequential modules, e.g., TCNs, RNNs, and Transformers. Empirical results demonstrate how a simple and elegant model with proper inductive basis can compare favorably w.r.t. the state of the art with elaborate designs, while being much more interpretable and computationally efficient for spatial-temporal forecasting problem. We hope our findings would open new horizons for future studies to revisit the design of more concise neural forecasting architectures.


page 1

page 3

page 5

page 7

page 8

page 9

page 10


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 Forecasting with Dynamic Graph Neural ODEs

Multivariate time series forecasting has long received significant atten...

A Study of Joint Graph Inference and Forecasting

We study a recent class of models which uses graph neural networks (GNNs...

Minimalist Traffic Prediction: Linear Layer Is All You Need

Traffic prediction is essential for the progression of Intelligent Trans...

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

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

Optimal Neural Network Feature Selection for Spatial-Temporal Forecasting

In this paper, we show empirical evidence on how to construct the optima...

Enhancing Spatiotemporal Prediction Model using Modular Design and Beyond

Predictive learning uses a known state to generate a future state over a...

Please sign up or login with your details

Forgot password? Click here to reset