CSGAN: Modality-Aware Trajectory Generation via Clustering-based Sequence GAN

• Type of Material: Article
• Authors: Minxing Zhang, Emory University; Haowen Lin, University of Southern California; Shun Takagi, Kyoto University; Yang Cao, Hokkaido University; Cyrus Shahabi, University of Southern California; Li Xiong, Emory University
• Language: English
• Date: 2023-08-22
• Publisher: IEEE
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: 2023 IEEE
• Final Published Version (URL): https://doi.org/10.1109/mdm58254.2023.00032
• Title of Journal or Parent Work: 2023 24th IEEE International Conference on Mobile Data Management (MDM)
• Start Page: 148
• End Page: 157
• Grant/Funding Information: Research supported by National Science Foundation (NSF) under CNS-2125530, National Institute of Health (NIH) under grant 5R01LM014026, JST SICORP JPMJSC2107, JSPS KAKENHI 22H03595, the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DOI/IBC) contract number 140D0423C0033, and an unrestricted cash gift from Microsoft Research.
• Keywords: Generative Adversarial Networks; Clustering; Synthetic Trajectory Generation; Reinforcement Learning
• Research Categories: Artificial Intelligence; Transportation

Abstract

Human mobility data is useful for various applications in urban planning, transportation, and public health, but collecting and sharing real-world trajectories can be challenging due to privacy and data quality issues. To address these problems, recent research focuses on generating synthetic trajectories, mainly using generative adversarial networks (GANs) trained by real-world trajectories. In this paper, we hypothesize that by explicitly capturing the modality of transportation (e.g., walking, biking, driving), we can generate not only more diverse and representative trajectories for different modalities but also more realistic trajectories that preserve the geographical density, trajectory, and transition level properties by capturing both cross-modality and modality-specific patterns. Towards this end, we propose a Clustering-based Sequence Generative Adversarial Network (CSGAN)1 that simultaneously clusters the trajectories based on their modalities and learns the essential properties of real-world trajectories to generate realistic and representative synthetic trajectories. To measure the effectiveness of generated trajectories, in addition to typical density and trajectory level statistics, we define several new metrics for a comprehensive evaluation, including modality distribution and transition probabilities both globally and within each modality. Our extensive experiments with real-world datasets show the superiority of our model in various metrics over state-of-the-art models.