Affiliation:
1. Tsinghua University, China
Abstract
Modern location-based systems have stimulated explosive growth of urban trajectory data and promoted many real-world applications,
e.g.
, trajectory prediction. However, heavy big data processing overhead and privacy concerns hinder trajectory acquisition and utilization. Inspired by regular trajectory distribution on transportation road networks, we propose to model trajectory data privately with a deep generative model and leverage the model to generate representative trajectories for downstream tasks or directly support these tasks (
e.g.
, popularity ranking), rather than acquiring and processing the original big trajectory data. Nevertheless, it is rather challenging to model high-dimensional trajectories with time-varying yet skewed distribution. To address this problem, we model and generate trajectory sequence with judiciously encoded spatio-temporal features over skewed distribution by leveraging an important factor neglected by the literature - the underlying road properties (
e.g.
, road types and directions), which are closely related to trajectory distribution. Specifically, we decompose trajectory into map-matched road sequence with temporal information and embed them to encode spatio-temporal features. Then, we enhance trajectory representation by encoding inherent route planning patterns from the underlying road properties. Later, we encode spatial correlations among edges and daily and weekly temporal periodicity information. Next, we employ a meta-learning module to generate trajectory sequence step by step by learning generalized trajectory distribution patterns from skewed trajectory data based on the well-encoded trajectory prefix. Last but not least, we preserve trajectory privacy by learning the model differential privately with clipping gradients. Experiments on real-world datasets show that our method significantly outperforms existing methods.
Publisher
Association for Computing Machinery (ACM)
Subject
General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development
Reference60 articles.
1. Martin Abadi Andy Chu Ian Goodfellow H Brendan McMahan Ilya Mironov Kunal Talwar and Li Zhang. 2016. Deep learning with differential privacy. In SIGSAC. 308--318. Martin Abadi Andy Chu Ian Goodfellow H Brendan McMahan Ilya Mironov Kunal Talwar and Li Zhang. 2016. Deep learning with differential privacy. In SIGSAC. 308--318.
2. Michael Balmer Marcel Rieser Konrad Meister David Charypar Nicolas Lefebvre and Kai Nagel. 2009. MATSim-T: Architecture and simulation times. In Multi-agent systems for traffic and transportation engineering. IGI Global 57--78. Michael Balmer Marcel Rieser Konrad Meister David Charypar Nicolas Lefebvre and Kai Nagel. 2009. MATSim-T: Architecture and simulation times. In Multi-agent systems for traffic and transportation engineering. IGI Global 57--78.
3. Mitra Baratchi , Nirvana Meratnia , Paul JM Havinga , Andrew K Skidmore, and Bert AKG Toxopeus. 2014 . A hierarchical hidden semi-Markov model for modeling mobility data. In UbiComp . 401--412. Mitra Baratchi, Nirvana Meratnia, Paul JM Havinga, Andrew K Skidmore, and Bert AKG Toxopeus. 2014. A hierarchical hidden semi-Markov model for modeling mobility data. In UbiComp. 401--412.
4. Amos Beimel , Shiva Prasad Kasiviswanathan , and Kobbi Nissim . 2010 . Bounds on the sample complexity for private learning and private data release . In Theory of Cryptography Conference. Springer, 437--454 . Amos Beimel, Shiva Prasad Kasiviswanathan, and Kobbi Nissim. 2010. Bounds on the sample complexity for private learning and private data release. In Theory of Cryptography Conference. Springer, 437--454.
5. Tolga Bektaş , Emrah Demir , and Gilbert Laporte . 2016. Green vehicle routing . In Green transportation logistics . Springer , 243--265. Tolga Bektaş, Emrah Demir, and Gilbert Laporte. 2016. Green vehicle routing. In Green transportation logistics. Springer, 243--265.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献