LEARNABLE GRAPH CONVOLUTIONAL NETWORK FOR TRAFFIC FORECASTING APPLICATIONS

Jiale Wang, Bi Yu Chen, William H.K. Lam, Chaoyang Shi, Wen Xin Ten

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Accurate and timely traffic forecasting has been a critically important topic in intelligent transportation systems. Considering the road network topology, various graph convolution network based deep learning models have been proposed. However, existing methods have insufficient interpretability and weak capability when modelling the heterogeneous spatial dependence. In this paper, a multi-temporal learnable graph convolution network (MT-LGC) model is proposed to solve the network-based traffic forecasting problem. The MT-LGC consists of three independent components. Each component integrates a learnable graph convolution (LGC) network for learning the heterogenous spatial dependence and a long short-term memory (LSTM) network for temporal dependence modelling. Experiments on two real-world traffic datasets show that our model MT-LGC outperforms the state-of-the-art baselines. Results of case studies also show that the proposed LGC can be integrated into these state-of-the-art methods as a general graph convolution operator and can achieve higher forecasting accuracy.

Original languageEnglish
Title of host publicationProceedings of the 25th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2021
Subtitle of host publicationSustainable Mobility
EditorsRyan C.P. Wong, Jiangping Zhou, W.Y. Szeto
PublisherHong Kong Society for Transportation Studies Limited
Pages11-17
Number of pages7
ISBN (Electronic)9789881581495
Publication statusPublished - 2021
Event25th International Conference of Hong Kong Society for Transportation Studies: Sustainable Mobility, HKSTS 2021 - Hong Kong, Hong Kong
Duration: 9 Dec 202110 Dec 2021

Publication series

NameProceedings of the 25th International Conference of Hong Kong Society for Transportation Studies, HKSTS 2021: Sustainable Mobility

Conference

Conference25th International Conference of Hong Kong Society for Transportation Studies: Sustainable Mobility, HKSTS 2021
Country/TerritoryHong Kong
CityHong Kong
Period9/12/2110/12/21

Keywords

  • Graph convolution network
  • Heterogenous
  • LSTM
  • Spatiotemporal dependency
  • Traffic forecasting

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Civil and Structural Engineering
  • Building and Construction
  • Transportation

Cite this