A Spatial-Temporal Dynamic Graph Attention Network Based Method for Sharing Travel Demand Prediction

PIAN Wei-guo; WU Ying-bo; CHEN Meng; CAI Jun-peng

doi:10.12263/DZXB.20210179

您当前的位置：

首页 >

文章列表页 >

A Spatial-Temporal Dynamic Graph Attention Network Based Method for Sharing Travel Demand Prediction

PAPERS | 更新时间：2025-12-08

- A Spatial-Temporal Dynamic Graph Attention Network Based Method for Sharing Travel Demand Prediction
- ACTA ELECTRONICA SINICA Vol. 50, Issue 2, Pages: 432-439(2022)
- 作者机构：
  
  1.重庆大学汽车协同创新中心，重庆 400044
  2.重庆大学大数据与软件学院，重庆 400044
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20210179
  CLC： TP399;U495
- Received：27 January 2021，
  
  Revised：2021-03-10，
  
  Published：25 February 2022
- 稿件说明：
移动端阅览
骈纬国,吴映波,陈蒙等.一种基于时空动态图注意力网络的共享出行需求预测方法[J].电子学报,2022,50(02):432-439.

PIAN Wei-guo,WU Ying-bo,CHEN Meng,et al.A Spatial-Temporal Dynamic Graph Attention Network Based Method for Sharing Travel Demand Prediction[J].ACTA ELECTRONICA SINICA,2022,50(02):432-439.
骈纬国,吴映波,陈蒙等.一种基于时空动态图注意力网络的共享出行需求预测方法[J].电子学报,2022,50(02):432-439. DOI： 10.12263/DZXB.20210179.

PIAN Wei-guo,WU Ying-bo,CHEN Meng,et al.A Spatial-Temporal Dynamic Graph Attention Network Based Method for Sharing Travel Demand Prediction[J].ACTA ELECTRONICA SINICA,2022,50(02):432-439. DOI： 10.12263/DZXB.20210179.

摘要

基于图卷积神经网络的共享出行需求预测一般采用非时间特定性的静态空间图结构提取非欧氏空间相关性特征，这种方式所构建的城市结构图是一种在不同时间间隔的静态空间图结构，而不能动态提取不同时间间隔的空间相关性特征.针对这一问题，本文提出了一种基于时空动态图注意力网络（Spatial-Temporal Dynamic Graph Attention Networks，STDGAT）的共享出行需求预测方法.该方法基于区域间通勤关系动态构建时间特定性城市空间图结构，以实现动态空间相关性建模，并采用图注意力网络和长短期记忆网络自适应提取动态空间相关性特征和时间依赖性特征.使用一个全连接层作为输出预测层将联合时空特征映射为真实的需求值以完成预测.实验结果表明，该方法在RMSE，MAPE和MAE等3个评价指标上均优于实验基准比较方法.

Abstract

Sharing travel demand prediction methods based on graph convolutional network generally adopt non-time-specific static graph structure to extract non-Euclidean spatial features. The urban structure graph in this way is a static spatial graph structure at different time intervals

which cannot extract spatial feature at different time intervals dynamically. To tackle this problem

this paper proposes a spatial-temporal dynamic graph attention network(STDGAT) for sharing travel demand prediction. STDGAT constructs a commuting-based time-specific dynamic graph structure to achieve the dynamic spatial correlation modeling. After that

STDGAT applies graph attention network and the long short-term memory to adaptively extract the dynamic spatial feature and temporal feature respectively. A fully connected layer is used as the prediction layer to map the joint spatial-temporal feature to real demand values. Experiment results demonstrate the significant improvement of our method on three evaluation metrics RMSE

MAPE

and MAE over state-of-the-art baselines.

关键词

Keywords

references

GENG X ， LI Y ， WANG L ， et al . Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting [C]// Proceedings of the AAAI Conference on Artificial Intelligence . Hawaii， USA : AAAI ， 2019 ， 33 : 3656 - 3663 .

YU B ， YIN H ， ZHU Z . Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting [C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence . Stockholm， Sweden : Morgan Kaufmann ， 2018 : 3634 - 3640 .

LI Y ， YU R ， SHAHABI C ， et al . Diffusion convolutional recurrent neural network: Data-driven traffic forecasting [C]// International Conference on Learning Representations . Vancouver， Canada : Vancouver Convention Center ， 2018 : 1 - 16 .

VELIČKOVIĆ P ， CUCURULL G ， CASANOVA A ， et al . Graph attention networks [C]// International Conference on Learning Representations . Vancouver， Canada . 2018 : 1 - 12 .

VASWANI A ， SHAZEER N ， PARMAR N ， et al . Attention is all you need [C]// Annual Conference on Neural Information Processing Systems(NeurIPS) . Long Beach， USA : MIT Press ， 2017 : 5998 - 6008 .

MOREIRA-MATIAS L ， GAMA J ， FERREIRAM ， et al . Predicting taxi-passenger demand using streaming data [J]. IEEE Transactions on Intelligent Transportation Systems ， 2013 ， 14 ( 3 ): 1393 - 1402 .

SHEKHAR S ， WILLIAMS B M . Adaptive seasonal time series models for forecasting short-term traffic flow [J]. Transportation Research Record ， 2007 ， 2024 ( 1 ): 116 - 125 .

胡文斌，聂聪，邱振宇，等 . 一种城市交通路网实时动态多路口路径导航量子搜索方法 [J]. 电子学报， 2018 ， 46 ( 1 ): 104 - 109 .

HU W B ， NIE C ， QIU Z Y ， et al . A route guidance method based on quantum searching for real-time dynamic multi-intersections in urban traffic networks [J]. Acta Electronica Sinica ， 2018 ， 46 ( 1 ): 104 - 109 . （in Chinese）

ZHANG J ， ZHENG Y ， QI D ， et al . DNN-based prediction model for spatio-temporal data [C]// Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . Burlingame， USA : ACM ， 2016 : 1 - 4 .

ZHANG J ， ZHENG Y ， QI D . Deep spatio-temporal residual networks for citywide crowd flows prediction [C]// Proceedings of the AAAI Conference on Artificial Intelligence . San Francisco， USA : AAAI ， 2017 : 1655 - 1661 .

PAN B ， DEMIRYUREK U ， SHAHABI C . Utilizing real-world transportation data for accurate traffic prediction [C]// 2012 IEEE 12th International Conference on Data Mining . Brussels， Belgium : IEEE ， 2012 : 595 - 604 .

WU F ， WANG H ， LI Z . Interpreting traffic dynamics using ubiquitous urban data [C]// Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . Burlingame， USA : ACM ， 2016 : 1 - 4 .

HE K ， ZHANG X ， REN S ， et al . Deep residual learning for image recognition [C]// Proceedings of the IEEE conference on computer vision and pattern recognition . Las Vegas， USA : IEEE ， 2016 : 770 - 778 .

WANG D ， CAO W ， LI J ， et al . DeepSD: Supply-demand prediction for online car-hailing services using deep neural network [C]// 2017 IEEE 33rd International Conference on Data Engineering . San Diego， USA : IEEE ， 2017 : 243 - 254 .

YU R ， LI Y ， SHAHABI C ， et al . Deep learning: A generic approach for extreme condition traffic forecasting [C]// Proceedings of the 2017 SIAM international Conference on Data Mining . Houston， USA : SIAM ， 2017 : 777 - 785 .

ZHAO J ， XU J ， ZHOU R ， et al . On prediction of user destination by sub-trajectory understanding: A deep learning based approach [C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management . Lingotto， Italy : ACM ， 2018 : 1413 - 1422 .

YAO H ， WU F ， KE J ， et al . Deep multi-view spatial-temporal network for taxi demand prediction [C]// Proceedings of the AAAI Conference on Artificial Intelligence . New Orleans， USA : AAAI ， 2018 : 1 - 9 .

QIU Z ， LIU L ， LI G ， et al . Taxi origin-destination demand prediction with contextualized spatial-temporal network [C]// 2019 IEEE International Conference on Multimedia and Expo . Shanghai， China : IEEE ， 2019 : 760 - 765 .

SUTSKEVER I ， VINYALS O ， LE Q V . Sequence to sequence learning with neural networks [C]// Annual Conference on Neural Information Processing Systems . Montreal， Canada : MIT Press ， 2014 : 3104 - 3112 .

HOCHREITER S ， BENGIO Y ， FRASCONI P ， et al . Gradient Flow in Recurrent Nets: The Difficulty of Learning Long-term Dependencies [M]. Piscataway， NJ， USA : Wiley-IEEE Press ， 2001 .

HOCHREITER S ， SCHMIDHUBER J . Long short-term memory [J]. Neural computation ， 1997 ， 9 ( 8 ): 1735 - 1780 .

SHI X ， CHEN Z ， WANG H ， et al . Convolutional LSTM network: A machine learning approach for precipitation nowcasting [C]// Annual Conference on Neural Information Processing Systems . Montreal， Canada : MIT Press ， 2015 : 802 - 810 .

KINGMA D P ， BA J . Adam: A method for stochastic optimization [C]// International Conference on Learning Representations . San Diego， USA : JMLR ， 2015 : 1 - 15 .

PASZKE A ， GROSS S ， MASSA F ， et al . PyTorch: An imperative style， high-performance deep learning library [C]// Advances in Neural Information Processing Systems . Vancouver， Canada : MIT Press ， 2019 : 8026 - 8037 .

CHEN T ， GUESTRIN C . Xgboost: A scalable tree boosting system [C]// Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining . San Francisco， USA : ACM ， 2016 : 785 - 794 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Associations Prediction Algorithm of MiRNAs and Diseases Based on Heterogeneous Graph Attention Network

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Differentially Private with Sparse and Smooth Self-Distillation

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

Enhancing Multimodal Aspect-Based Sentiment Analysis with Adaptive Noise and Aspect Graph Association Learning

Related Author

LI Zheng-wei

LI Jia-shu

YOU Zhu-hong

NIE Ru

ZHAO Huan

ZHONG Tang-bo

HUANG Yu-zhe

GUAN Yong-yuan

Related Institution

Engineering Research Center of Mine Digitalization of Ministry of Education, China University of Mining and Technology

School of Computer Science and Technology, China University of Mining and Technology

School of Computer Science, Northwestern Polytechnical University

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

School of Information, Renmin University of China

⁰