mlsanityData to 7 Oct 2026

Graph Neural Rough Differential Equations for Traffic Forecasting

arXiv 2303.10909 ↗First posted 20 Mar 2023cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 29 of its 73 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

29 of 73 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  9. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  10. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  11. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  12. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
17 more
  1. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  2. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 209
  3. 2017Deep Learning for Precipitation Nowcasting: A Benchmark and A New Modelcited by 180
  4. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 179
  5. 2020Neural Rough Differential Equations for Long Time Seriescited by 140
  6. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  7. 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
  8. 2019STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecastingcited by 59
  9. 2019Predicting Path Failure In Time-Evolving Graphscited by 54
  10. 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
  11. 2021Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkcited by 52
  12. 2022Blurring-Sharpening Process Models for Collaborative Filteringcited by 35
  13. 2016Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasetscited by 31
  14. 2018Exascale Deep Learning for Climate Analyticscited by 28
  15. 2021Climate Modeling with Neural Diffusion Equationscited by 20
  16. 2020Two-stage Training of Graph Neural Networks for Graph Classificationcited by 4
  17. 2021Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanismscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 3; 2026: 4.

14 papers.

Sort:

By area:

  1. 2024PANDA: Expanded Width-Aware Message Passing Beyond Rewiringcited by 10
  2. 2023Continuous-time Autoencoders for Regular and Irregular Time Series Imputationcited by 6
  3. 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learningcited by 3
  4. 2024Variational Mode-Driven Graph Convolutional Network for Spatiotemporal Traffic Forecastingcited by 2
  5. 2023Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equationscited by 1
  6. 2024Bridging Dynamic Factor Models and Neural Controlled Differential Equations for Nowcasting GDPcited by 1
  7. 2024Deep Signature: Characterization of Large-Scale Molecular Dynamicscited by 0
  8. 2024ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equationscited by 0
  9. 2025MHGNet: Multi-Heterogeneous Graph Neural Network for Traffic Predictioncited by 0
  10. 2025FacePhys: State of the Heart Learningcited by 0
  11. 2026Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEscited by 0
  12. 2026Continuous Cross-Domain Traffic State Prediction via Memory-Augmented Graph Liquid Time-Constant Networkscited by 0
2 more
  1. 2026INDEQS: Informed Neural controlled Differential EQuationScited by 0
  2. 2026STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecastingcited by 0