Graph Neural Controlled Differential Equations for Traffic Forecasting

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