Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/95976
PIRA download icon_1.1View/Download Full Text
Title: Domain Adversarial Spatial-Temporal Network : a transferable framework for short-term traffic forecasting across cities
Authors: Tang, Y
Qu, A
Chow, AHF
Lam, WHK 
Wong, SC
Ma, W 
Issue Date: 17-Oct-2022
Source: In CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, p. 1905-1915. New York, NY, USA: Association for Computing Machinery, 2022
Abstract: Accurate real-time traffic forecast is critical for intelligent transportation systems (ITS) and it serves as the cornerstone of various smart mobility applications. Though this research area is dominated by deep learning, recent studies indicate that the accuracy improvement by developing new model structures is becoming marginal. Instead, we envision that the improvement can be achieved by transferring the “forecasting-related knowledge” across cities with different data distributions and network topologies. To this end, this paper aims to propose a novel transferable traffic forecasting framework: Domain Adversarial Spatial-Temporal Network (DastNet). DastNet is pre-trained on multiple source networks and fine-tuned with the target network’s traffic data. Specifically, we leverage the graph representation learning and adversarial domain adaptation techniques to learn the domain-invariant node embeddings, which are further incorporated to model the temporal traffic data. To the best of our knowledge, we are the first to employ adversarial multi-domain adaptation for network-wide traffic forecasting problems. DastNet consistently outperforms all state-of-the-art baseline methods on three benchmark datasets. The trained DastNet is applied to Hong Kong’s new traffic detectors, and accurate traffic predictions can be delivered immediately (within one day) when the detector is available. Overall, this study suggests an alternative to enhance the traffic forecasting methods and provides practical implications for cities lacking historical traffic data. Source codes of DastNet are available at https://github.com/YihongT/DASTNet.
Keywords: Traffic forecasting
Transfer learning
Domain adaptation
Adversarial learning
Intelligent transportation systems
Publisher: Association for Computing Machinery
ISBN: 978-1-4503-9236-5
DOI: 10.1145/3511808.3557294
Description: CIKM '22: The 31st ACM International Conference on Information and Knowledge Management, Atlanta, GA, USA, October 17 - 21, 2022
Rights: © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, http://dx.doi.org/10.1145/3511808.3557294.
The following publication 2022. Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Association for Computing Machinery, New York, NY, USA is available at https://dl.acm.org/doi/abs/10.1145/3511808.3557294.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
Tang_Transferable_Traffic_Forecasting.pdfPre-Published version5.38 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Final Accepted Manuscript
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

83
Last Week
1
Last month
Citations as of Mar 24, 2024

Downloads

33
Citations as of Mar 24, 2024

SCOPUSTM   
Citations

4
Citations as of Mar 29, 2024

WEB OF SCIENCETM
Citations

4
Citations as of Mar 28, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.