LibCity: An Open Library for Urban Spatial-temporal Data Mining

GMAN: A Graph Multi-Attention Network for Traffic Prediction (GMAN, https://fanxlxmu.github.io/publication/aaai2020/) was accepted by AAAI-2020.

[TKDD 2023] Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

[AAAI2023] A PyTorch implementation of PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction.

[IJCAI-24] Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting

This repo includes introduction, code and dataset of our paper Deep Sequence Learning with Auxiliary Information for Traffic Prediction (KDD 2018).

Traffic data processing tools in LibCity

Useful resources for traffic prediction, including popular papers, datasets, tutorials, toolkits, and other helpful repositories.

HetETA: Heterogeneous Information Network Embedding for Estimating Time of Arrival

[Pattern Recognition] Decomposition Dynamic Graph Conolutional Recurrent Network for Traffic Forecasting

[SIGKDD'2025] Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

[CIKM'2023] "STExplainer: Explainable Spatio-Temporal Graph Neural Networks"

Predict traffic flow with LSTM. For experimental purposes only, unsupported!

[CIKM 2022] Source codes of CIKM2022 Full Paper "Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities"

[Neural Networks] RGDAN: A random graph diffusion attention network for traffic prediction

[TITS2025] Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction

Traffic prediction with graph neural network using PyTorch Geometric. The implementation uses the MetaLayer class to build the GNN which allows for separate edge, node and global models.

Repository for advanced traffic forecasting models integrating GCN, LSTM/Bi-LSTM, and attention mechanisms for improved accuracy, including weather data processing.

[CIKM'2023] "CL4ST: Spatio-Temporal Meta Contrastive Learning"

[Neural Networks] PDG2Seq: Periodic Dynamic Graph to Sequence model for Traffic Flow Prediction