TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Graph Neural Controlled Differential Equations for Traffic...

Graph Neural Controlled Differential Equations for Traffic Forecasting

Jeongwhan Choi, Hwangyong Choi, Jeehyun Hwang, Noseong Park

2021-12-07Spatio-Temporal ForecastingTraffic PredictionWeather ForecastingTime Series Forecasting
PaperPDFCode(official)

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.

Results

TaskDatasetMetricValueModel
Traffic PredictionPeMSD7(M)12 steps MAE2.68STG-NCDE
Traffic PredictionPeMSD7(M)12 steps MAPE6.76STG-NCDE
Traffic PredictionPeMSD7(M)12 steps RMSE5.39STG-NCDE
Traffic PredictionPeMSD412 steps MAE19.21STG-NCDE
Traffic PredictionPeMSD412 steps MAPE12.76STG-NCDE
Traffic PredictionPeMSD412 steps RMSE31.09STG-NCDE
Traffic PredictionPeMSD7(L)12 steps MAE2.87STG-NCDE
Traffic PredictionPeMSD7(L)12 steps MAPE7.31STG-NCDE
Traffic PredictionPeMSD7(L)12 steps RMSE5.76STG-NCDE
Traffic PredictionPeMSD812 steps MAE15.45STG-NCDE
Traffic PredictionPeMSD812 steps MAPE9.92STG-NCDE
Traffic PredictionPeMSD812 steps RMSE24.81STG-NCDE
Traffic PredictionPeMSD712 steps MAE20.53STG-NCDE
Traffic PredictionPeMSD712 steps MAPE8.8STG-NCDE
Traffic PredictionPeMSD712 steps RMSE33.84STG-NCDE
Traffic PredictionPeMSD312 steps MAE15.57STG-NCDE
Traffic PredictionPeMSD312 steps MAPE15.06STG-NCDE
Traffic PredictionPeMSD312 steps RMSE27.09STG-NCDE

Related Papers

The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting2025-07-17FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale2025-07-16D3FL: Data Distribution and Detrending for Robust Federated Learning in Non-linear Time-series Data2025-07-15Data Augmentation in Time Series Forecasting through Inverted Framework2025-07-15Federated Learning with Graph-Based Aggregation for Traffic Forecasting2025-07-13MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models2025-07-09Foundation models for time series forecasting: Application in conformal prediction2025-07-09Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching2025-07-09