Graph Neural Controlled Differential Equations for Traffic Forecasting

TL;DR

This paper introduces STG-NCDE, a novel spatio-temporal graph neural controlled differential equation model that significantly improves traffic forecasting accuracy by integrating temporal and spatial NCDEs.

Contribution

The paper proposes a new framework combining two neural controlled differential equations for better spatio-temporal processing in traffic forecasting.

Findings

Outperforms 20 baseline models across 6 datasets

Achieves the best accuracy in all benchmark tests

Demonstrates the effectiveness of NCDEs in spatio-temporal tasks

Abstract

Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present the method of spatio-temporal graph neural controlled differential equation (STG-NCDE). Neural controlled differential equations (NCDEs) are a breakthrough concept for processing sequential data. We extend the concept and design two NCDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 20 baselines. STG-NCDE shows the best accuracy in all cases, outperforming all those 20 baselines by non-trivial margins.