Attention-Based Local-Global Hypergraph Convolutional Network for Traffic Flow Forecasting

Yu Zhao, Fan Ding*, Huachun Tan

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Traffic flow forecasting is of significance for traffic control and management. In recent years, researchers have widely utilized data-driven spatio-temporal graph neural networks (GNNs) to capture the complex spatio-temporal characteristics of traffic flow and achieve accurate prediction outcomes. However, GNNs fail to capture non-paired relationships, and previous studies struggle to encompass both local and global dependencies. To address these limitations, we introduce a novel attention-based local-global hypergraph convolutional network (ALGHGCN) for traffic flow forecasting. Specifically, to handle spatial dependencies, the proposed model incorporates well-designed spatial convolution blocks that integrate the attention mechanism. These blocks capture non-paired dependencies using local hypergraphs constructed from road networks as well as global hypergraphs created from historical time series. Additionally, a temporal attention block is employed to exploit relationships for temporal dependencies. Comparative analysis against multiple baselines using real-world data sets demonstrates the superior performance of the proposed ALGHGCN model.

Original languageEnglish
Title of host publicationCICTP 2024
Subtitle of host publicationResilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation - Proceedings of the 24th COTA International Conference of Transportation Professionals
EditorsJianming Ma, Qin Luo, Lijun Sun, Baicheng Li, Jingjing Chen, Guohui Zhang
PublisherAmerican Society of Civil Engineers (ASCE)
Pages1643-1653
Number of pages11
ISBN (Electronic)9780784485484
DOIs
Publication statusPublished - 2024
Event24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024 - Shenzhen, China
Duration: 23 Jul 202426 Jul 2024

Publication series

NameCICTP 2024: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation - Proceedings of the 24th COTA International Conference of Transportation Professionals

Conference

Conference24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024
Country/TerritoryChina
CityShenzhen
Period23/07/2426/07/24

Fingerprint

Dive into the research topics of 'Attention-Based Local-Global Hypergraph Convolutional Network for Traffic Flow Forecasting'. Together they form a unique fingerprint.

Cite this