Conference proceeding
STrans-GAN: Spatially-Transferable Generative Adversarial Networks for Urban Traffic Estimation
2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), pp.743-752
IEEE International Conference on Data Mining
01/01/2022
DOI: 10.1109/ICDM54844.2022.00085
Abstract
Conditional traffic estimation is a vital problem in urban plan deployment, which can help evaluate urban construction plans and improve transportation efficiency. Conventional methods for conditional traffic estimation usually focus on supervised settings, which require a large amount of labeled training data. However, in many urban planning applications, the large amount of traffic data in a new city can be hard or impossible to acquire. To tackle the conditional traffic estimation problem in data scarcity situations, we formulate the problem as a spatial transfer generative learning problem. Compared to prior spatial transfer learning frameworks with only single source city, we propose to extracts knowledge from multiple source cities to improve the estimation accuracy and transfer stability, which is a technically more challenging task. As a solution, we propose a new cross-city conditional traffic estimation method - SpatiallyTransferable Generative Adversarial Networks (STrans-GAN) with novel pre-training and fine-tuning algorithms. STransGAN preserves diverse traffic patterns from multiple source cities through traffic clustering, and incorporates meta-learning idea into the pre-training process to learn a well-generalized model. During fine-tuning, we propose to add a cluster matching regularizer to realize the flexible adaptation in different scenarios. Through extensive experiments on multiple-city datasets, the effectiveness of STrans-GAN is proved.
Details
- Title: Subtitle
- STrans-GAN: Spatially-Transferable Generative Adversarial Networks for Urban Traffic Estimation
- Creators
- Yingxue Zhang - Binghamton UniversityYanhua Li - Worcester Polytechnic InstituteXun Zhou - University of IowaXiangnan Kong - Worcester Polytechnic InstituteJun Luo - Lenovo
- Contributors
- Xingquan Zhu (Editor)Sanjay Ranka (Editor)My T Thai (Editor)Takashi Washio (Editor)Xindong Wu (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- 2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), pp.743-752
- Publisher
- IEEE
- Series
- IEEE International Conference on Data Mining
- DOI
- 10.1109/ICDM54844.2022.00085
- ISSN
- 1550-4786
- eISSN
- 2374-8486
- Number of pages
- 10
- Grant note
- Safety Research using Simulation University Transportation Center (SAFER-SIM) 69A3551747131 / U.S. Department of Transportation's University Transportation Centers Program IIS-1942680; CNS-1952085; CMMI1831140; DGE-2021871 / NSF; National Science Foundation (NSF) DB210100743 / ARC Discovery Project; Australian Research Council
- Language
- English
- Date published
- 01/01/2022
- Academic Unit
- Business Analytics
- Record Identifier
- 9984419650802771
Metrics
3 Record Views