Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

time-series-4

Traffic Prediction

3260 papers • 126 benchmarks • 313 datasets

Traffic Prediction is a task that involves forecasting traffic conditions, such as the volume of vehicles and travel time, in a specific area or along a particular road. This task is important for optimizing transportation systems and reducing traffic congestion. ( Image credit: BaiduTraffic )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in traffic-prediction-4

Trend

Dataset

Best Model

Actions

METR-LA

METR-LA

PeMS07

PeMS07

PEMS-BAY

PEMS-BAY

Libraries

i

Use these libraries to find traffic-prediction-4 models and implementations

benedekrozemberczki/pytorch_geometr…

5 papers 2,613

Datasets

PeMSD8

METR-LA

PeMS04

PEMS-BAY

PeMSD7

PeMS07

Subtasks

Traffic Data Imputation

Most implemented papers

Sequence to Sequence Learning with Neural Networks

Quoc V. Le, O. Vinyals, I. Sutskever•Tue Sep 09 2014

This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

21470

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

PeMSD4

PeMSD4

PeMS08

PeMS08

PeMSD8

PeMSD8

PeMSD7

PeMSD7

PeMS04

PeMS04

PeMSD7(M)

PeMSD7(M)

NE-BJ

NE-BJ

PeMS-M

PeMS-M

PeMSD3

PeMSD3

PeMSD7(L)

PeMSD7(L)

NYCTaxi

NYCTaxi

BJTaxi

BJTaxi

SZ-Taxi

SZ-Taxi

NYCBike1

NYCBike1

NYCBike2

NYCBike2

Q-Traffic

Q-Traffic

PeMSD4 (10 days' training data, 15min)

PeMSD4 (10 days' training data, 15min)

PeMSD4 (10 days' training data, 30min)

PeMSD4 (10 days' training data, 30min)

PeMSD4 (10 days' training data, 60min)

PeMSD4 (10 days' training data, 60min)

PeMSD7 (10 days' training data, 15min)

PeMSD7 (10 days' training data, 15min)

PeMSD7 (10 days' training data, 30min)

PeMSD7 (10 days' training data, 30min)

PeMSD7 (10 days' training data, 60min)

PeMSD7 (10 days' training data, 60min)

PeMSD8 (10 days' training data, 15min)

PeMSD8 (10 days' training data, 15min)

PeMSD8 (10 days' training data, 30min)

PeMSD8 (10 days' training data, 30min)

PeMSD8 (10 days' training data, 60min)

PeMSD8 (10 days' training data, 60min)

HZME(inflow)

HZME(inflow)

HZME(outflow)

HZME(outflow)

EXPY-TKY

EXPY-TKY

Beijing Traffic

Beijing Traffic

LargeST

LargeST

2 papers 177

PeMSD4

PeMSD4

LargeST

NYCTaxi

PeMS08

0

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Yaguang Li, Rose Yu, C. Shahabi, Yan Liu•Wed Jul 05 2017

Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow and evaluates the framework on two real-world large scale road network traffic datasets and observes consistent improvement.

3698 0

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang, Zonghan Wu•Thu May 30 2019

This paper proposes a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling by developing a novel adaptive dependency matrix and learn it through node embedding, which can precisely capture the hidden spatial dependency in the data.

2800 0

GMAN: A Graph Multi-Attention Network for Traffic Prediction

Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, Jianzhong Qi•Sun Nov 10 2019

Experimental results on two real-world traffic prediction tasks demonstrate the superiority of GMAN, and in the 1 hour ahead prediction, GMAN outperforms state-of-the-art methods by up to 4% improvement in MAE measure.

1722 0

Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

Guanjie Zheng, Z. Li, Huaxiu Yao, Xianfeng Tang, Hua Wei•Fri Mar 02 2018

A novel Spatial-Temporal Dynamic Network (STDN) is proposed, in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting.

802 0

Incrementally Improving Graph WaveNet Performance on Traffic Prediction

Clara H. McCreery, Sam Shleifer, Vamsi Chitters•Tue Dec 10 2019

This work improves GWN by using better hyperparameters, adding connections that allow larger gradients to flow back to the early convolutional layers, and pretraining on an easier short-term traffic prediction task, and shows that ensembling separate models for short- and long-term predictions further improves performance.

25 0

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

Ailing Zeng, Qiang Xu, Minhao Liu, Mu-Hwa Chen, Zhijian Xu, Qiuxia Lai, Lingna Ma•Wed Jun 16 2021

A novel neural network architecture that conducts sample convolution and interaction for temporal modeling and forecasting, named SCINet, which is a recursive downsample-convolve-interact architecture that achieves significant forecasting accuracy improvements over both existing convolutional models and Transformer-based solutions across various real-world time series forecasting datasets.

661 0

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Lina Yao, Xianzhi Wang, Lei Bai, Can Li, Can Wang•Sun Jul 05 2020

It is argued that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable, and two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities are proposed.

1710 0

Adding a benchmark result helps the community track progress.

Traffic Prediction | State-of-the-Art