</> Code with Papers by Syntology

Papers › Graph Neural Controlled Differential Equations for Traffic Forecasting

Graph Neural Controlled Differential Equations for Traffic Forecasting

7 Dec 2021arXiv:2112.03558archive 2025-07-28

Jeongwhan Choi, Hwangyong Choi, Jeehyun Hwang, Noseong Park

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jeongwhanchoi/STG-NCDE officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Spatio-Temporal ForecastingTime Series ForecastingTraffic PredictionWeather Forecasting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Traffic Prediction PeMSD3 STG-NCDE 12 steps MAE 15.57 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD3 STG-NCDE 12 steps MAPE 15.06 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD3 STG-NCDE 12 steps RMSE 27.09 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NCDE 12 steps MAE 19.21 #13 of 13 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NCDE 12 steps MAPE 12.76 #13 of 13 Archive leaderboard report
Traffic Prediction PeMSD4 STG-NCDE 12 steps RMSE 31.09 #13 of 13 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NCDE 12 steps MAE 20.53 #8 of 8 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NCDE 12 steps MAPE 8.8 #8 of 8 Archive leaderboard report
Traffic Prediction PeMSD7 STG-NCDE 12 steps RMSE 33.84 #8 of 8 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NCDE 12 steps MAE 2.87 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NCDE 12 steps MAPE 7.31 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(L) STG-NCDE 12 steps RMSE 5.76 #6 of 6 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NCDE 12 steps MAE 2.68 #6 of 7 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NCDE 12 steps MAPE 6.76 #6 of 7 Archive leaderboard report
Traffic Prediction PeMSD7(M) STG-NCDE 12 steps RMSE 5.39 #6 of 7 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NCDE 12 steps MAE 15.45 #13 of 13 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NCDE 12 steps MAPE 9.92 #13 of 13 Archive leaderboard report
Traffic Prediction PeMSD8 STG-NCDE 12 steps RMSE 24.81 #13 of 13 Archive leaderboard report
Weather Forecasting NOAA Atmospheric Temperature Dataset STG-NCDE MAE (t+1) 0.3582 ± 0.0616 #5 of 5 Archive leaderboard report
Weather Forecasting NOAA Atmospheric Temperature Dataset STG-NCDE MAE (t+10) 1.4095 ± 0.1836 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GCNNODE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections