Traffic Flow Forecasting

Traffic flow forecasting aims to predict future traffic conditions using historical data and network structure, primarily focusing on improving prediction accuracy and efficiency. Current research heavily utilizes deep learning, particularly graph neural networks (GNNs) and transformers, often incorporating adaptive graph structures and multi-channel data fusion to capture complex spatio-temporal dependencies and address challenges like long-term prediction and evolving network conditions. Accurate traffic flow forecasting is crucial for intelligent transportation systems, enabling optimized traffic management, improved infrastructure planning, and enhanced public safety.

Papers

March 14, 2023

FPTN: Fast Pure Transformer Network for Traffic Flow Forecasting
Junhao Zhang, Junjie Tang, Juncheng Jin, Zehui Qu
Traffic Data Traffic Flow Forecasting Spatiotemporal Correlation Pure Transformer

February 17, 2023

Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting
Qingxiang Liu, Sheng Sun, Min Liu, Yuwei Wang, Bo Gao
Traffic Data Traffic Flow Forecasting Traffic State Sequence

September 21, 2022

DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems
Yixuan Sun, Christian Moya, Guang Lin, Meng Yue
Graph Neural Network Response Generation Zero Shot Transfer Traffic Flow Forecasting Deep Operator Networked System DeepONet Framework

July 9, 2022

Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting
Aosong Feng, Leandros Tassiulas
Graph Transformer Traffic Forecasting Temporal Transformer Temporal Correlation Spatial Temporal Graph Adaptive Graph Traffic Flow Forecasting

June 19, 2022

Traffic-Twitter Transformer: A Nature Language Processing-joined Framework For Network-wide Traffic Forecasting
Meng-Ju Tsai, Zhiyong Cui, Hao Yang, Cole Kopca, Sophie Tien, Yinhai Wang
Traffic Prediction Traffic Forecasting Traffic Flow Forecasting Future Traffic Processing Framework Network Wide Traffic Long Term Traffic Forecasting

May 20, 2022

A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting
Weiguo Zhu, Yongqi Sun, Xintong Yi, Yan Wang
Total Correlation Temporal Correlation Spatiotemporal Representation Traffic Flow Forecasting Spatial Correlation Spatiotemporal Network

March 21, 2022

STCGAT: A Spatio-temporal Causal Graph Attention Network for traffic flow prediction in Intelligent Transportation Systems
Wei Zhao, Shiqi Zhang, Bing Zhou, Bei Wang
Temporal Dependency Traffic Prediction Intelligent Transportation System Traffic Flow Prediction Traffic Flow Forecasting

February 18, 2022

PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting
Yuyol Shin, Yoonjin Yoon
Traffic Prediction Traffic Forecasting Traffic Flow Forecasting Temporal Traffic Progressive Graph

December 6, 2021

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network
Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Chenxing Wang, Liang Zeng
Traffic Forecasting Wavelet Based Traffic Flow Forecasting Spectral Attention Accurate Traffic Forecasting

November 3, 2021

ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting
Xiao Yan, Xianghua Gan, Jingjing Tang, Rui Wang
Self Attention Traffic Flow Forecasting Traffic Video Free Transformer

Traffic Flow Forecasting

Papers

FPTN: Fast Pure Transformer Network for Traffic Flow Forecasting

Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting

DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems

Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting

Traffic-Twitter Transformer: A Nature Language Processing-joined Framework For Network-wide Traffic Forecasting

A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting

STCGAT: A Spatio-temporal Causal Graph Attention Network for traffic flow prediction in Intelligent Transportation Systems

PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network

ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting