Residential College | false |
Status | 已發表Published |
FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction | |
Yang, Linghua1; Chen, Wantong1; He, Xiaoxi2; Wei, Shuyue1; Xu, Yi3; Zhou, Zimu4; Tong, Yongxin1 | |
2024-08-24 | |
Conference Name | KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
Source Publication | KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining |
Pages | 6105–6116 |
Conference Date | August 25-29, 2024 |
Conference Place | Barcelona |
Country | Spain |
Publication Place | New York, NY, USA |
Publisher | Association for Computing Machinery |
Abstract | Graph-based methods have witnessed tremendous success in traffic prediction, largely attributed to their superior ability in capturing and modeling spatial dependencies. However, urban-scale traffic data are usually distributed among various owners, limited in sharing due to privacy restrictions. This fragmentation of data severely hinders interaction across clients, impeding the utilization of inter-client spatial dependencies. Existing studies have yet to address this non-trivial issue, thereby leading to sub-optimal performance. To fill this gap, we propose FedGTP, a new federated graph-based traffic prediction framework that promotes adaptive exploitation of inter-client spatial dependencies to recover close-to-optimal performance complying with privacy regulations like GDPR. We validate FedGTP via large-scale application-driven experiments on real-world datasets. Extensive baseline comparison, ablation study and case study demonstrate that FedGTP indeed surpasses existing methods through fully recovering inter-client spatial dependencies, achieving 21.08%, 13.48%, 19.90% decrease on RMSE, MAE and MAPE, respectively. Our code is available at https://github.com/LarryHawkingYoung/KDD2024_FedGTP |
Keyword | Federated Learning Traffic Prediction Spatial-temporal Graph Neural Network |
DOI | 10.1145/3637528.3671613 |
URL | View the original |
Language | 英語English |
Scopus ID | 2-s2.0-85203688672 |
Fulltext Access | |
Citation statistics | |
Document Type | Conference paper |
Collection | Faculty of Science and Technology DEPARTMENT OF ELECTRICAL AND COMPUTER ENGINEERING |
Corresponding Author | He, Xiaoxi; Tong, Yongxin |
Affiliation | 1.SKLCCSE Lab, Beihang University Beijing, China 2.Faculty of Science and Technology, University of Macau Macau, China 3.SKLCCSE Lab, Institute of Artificial Intelligence, Beihang University Beijing, China 4.School of Data Science, City University of Hong Kong Hong Kong, China |
Corresponding Author Affilication | Faculty of Science and Technology |
Recommended Citation GB/T 7714 | Yang, Linghua,Chen, Wantong,He, Xiaoxi,et al. FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction[C], New York, NY, USA:Association for Computing Machinery, 2024, 6105–6116. |
APA | Yang, Linghua., Chen, Wantong., He, Xiaoxi., Wei, Shuyue., Xu, Yi., Zhou, Zimu., & Tong, Yongxin (2024). FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction. KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 6105–6116. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment