Graph Neural Rough Differential Equations for Traffic Forecasting

2023/03/20 by Jeongwhan Choi, Choi, Jeongwhan, Noseong Park +1 · 1 citation
Computer Science · #Rough Sets and Fuzzy Logic #Image Processing and 3D Reconstruction #Statistical and Computational Modeling

paper · pdf · doi:10.48550/arxiv.2303.10909

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 rough differential equation (STG-NRDE). Neural rough differential equations (NRDEs) are a breakthrough concept for processing time-series data. Their main concept is to use the log-signature transform to convert a time-series sample into a relatively shorter series of feature vectors. We extend the concept and design two NRDEs: 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 27 baselines. STG-NRDE shows the best accuracy in all cases, outperforming all those 27 baselines by non-trivial margins.

Cited by

• FacePhys: State of the Heart Learning

Related

• Graph Neural Controlled Differential Equations for Traffic Forecasting
• Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations
• Continuously Evolving Graph Neural Controlled Differential Equations for Traffic Forecasting
• Do We Really Need Graph Neural Networks for Traffic Forecasting?
• Spatial-Temporal Hypergraph Neural Network for Traffic Forecasting