ABSTRACT
Human trajectories, reflecting people's travel patterns and the range of activities, are crucial for the applications like urban planning and epidemic control. However, the real-world human trajectory data tends to be limited by user privacy or device acquisition issues, leading to its insufficient quality to support the above applications. Hence, generating human trajectory data is a crucial but challenging task, which suffers from the following two critical challenges: 1) how to capture the user distribution in human trajectories (group view), and 2) how to model the complex mobility patterns of each user trajectory (individual view). In this paper, we propose a novel human trajectories generator (named VOLUNTEER), consisting of a user VAE and a trajectory VAE, to address the above challenges. Specifically, in the user VAE, we propose to learn the user distribution with all human trajectories from a group view. In the trajectory VAE, from the individual view, we model the complex mobility patterns by decoupling travel time and dwell time to accurately simulate individual trajectories. Extensive experiments on two real-world datasets show the superiority of our model over the state-of-the-art baselines. Further application analysis in the industrial system also demonstrates the effectiveness of our model.
Supplemental Material
- Yazan Abu Farha, Alexander Richard, and Juergen Gall. 2018. When will you do what?-anticipating temporal occurrences of activities. In Proc. CVPR.Google ScholarCross Ref
- Gergely Acs, Gergely Biczók, and Claude Castelluccia. 2018. Privacy-preserving release of spatio-temporal density. In Handbook of Mobile Data Privacy. 307--335.Google Scholar
- Miguel E Andrés, Nicolás E Bordenabe, Konstantinos Chatzikokolakis, and Catuscia Palamidessi. 2013. Geo-indistinguishability: Differential privacy for location-based systems. In Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security. 901--914.Google ScholarDigital Library
- Emmanuel Bacry, Thibault Jaisson, and Jean--Franois Muzy. 2016. Estimation of slowly decreasing Hawkes kernels: application to high-frequency order book dynamics. Quantitative Finance (2016), 1--23.Google Scholar
- Duygu Balcan and Alessandro Vespignani. 2011. Phase transitions in contagion processes mediated by recurrent mobility patterns. Nature physics, Vol. 7, 7 (2011), 581--586.Google Scholar
- Vincent Bindschaedler and Reza Shokri. 2016. Synthesizing plausible privacy-preserving location traces. In Proc. IEEE SP.Google ScholarCross Ref
- Xinyu Chen, Jiajie Xu, Rui Zhou, Wei Chen, Junhua Fang, and Chengfei Liu. 2021. TrajVAE: A Variational AutoEncoder model for trajectory generation. Neurocomputing, Vol. 428 (2021), 332--339.Google ScholarCross Ref
- Abhyuday Desai, Cynthia Freeman, Zuhui Wang, and Ian Beaver. 2021. Timevae: A variational auto-encoder for multivariate time series generation. arXiv preprint arXiv:2111.08095 (2021).Google Scholar
- Nan Du, Hanjun Dai, Rakshit Trivedi, Utkarsh Upadhyay, Manuel Gomez-Rodriguez, and Le Song. 2016. Recurrent marked temporal point processes: Embedding event history to vector. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 1555--1564.Google ScholarDigital Library
- Úlfar Erlingsson, Vasyl Pihur, and Aleksandra Korolova. 2014. Rappor: Randomized aggregatable privacy-preserving ordinal response. In Proceedings of the 2014 ACM SIGSAC conference on computer and communications security. 1054--1067.Google ScholarDigital Library
- Jie Feng, Zeyu Yang, Fengli Xu, Haisu Yu, Mudan Wang, and Yong Li. 2020a. Learning to Simulate Human Mobility. Proc. KDD (2020).Google ScholarDigital Library
- Jie Feng, Zeyu Yang, Fengli Xu, Haisu Yu, Mudan Wang, and Yong Li. 2020b. Learning to Simulate Human Mobility. In Proc. KDD.Google ScholarDigital Library
- Tianfu He, Jie Bao, Ruiyuan Li, Sijie Ruan, Yanhua Li, Li Song, Hui He, and Yu Zheng. 2020. What is the human mobility in a new city: Transfer mobility knowledge across cities. In Proceedings of The Web Conference 2020. 1355--1365.Google ScholarDigital Library
- Hsun-Ping Hsieh, Shou-De Lin, and Yu Zheng. 2015. Inferring air quality for station location recommendation based on urban big data. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. 437--446.Google ScholarDigital Library
- Dou Huang, Xuan Song, Zipei Fan, Renhe Jiang, and Yugo Kato. 2019. A Variational Autoencoder Based Generative Model of Urban Human Mobility. In Proc. MIPR.Google ScholarCross Ref
- Renhe Jiang, Xuan Song, Zipei Fan, Tianqi Xia, Zhaonan Wang, Quanjun Chen, Zekun Cai, and Ryosuke Shibasaki. 2021. Transfer urban human mobility via POI embedding over multiple cities. ACM Transactions on Data Science, Vol. 2, 1 (2021), 1--26.Google ScholarDigital Library
- Shan Jiang, Yingxiang Yang, Siddharth Gupta, Daniele Veneziano, Shounak Athavale, and Marta C González. 2016. The TimeGeo modeling framework for urban mobility without travel surveys. PNAS, Vol. 113, 37 (2016).Google ScholarCross Ref
- Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).Google Scholar
- Xiangjie Kong, Zhenzhen Xu, Guojiang Shen, Jinzhong Wang, Qiuyuan Yang, and Benshi Zhang. 2016. Urban traffic congestion estimation and prediction based on floating car trajectory data. Future Generation Computer Systems, Vol. 61 (2016), 97--107.Google ScholarDigital Library
- Vaibhav Kulkarni, Natasa Tagasovska, Thibault Vatter, and Benoit Garbinato. 2018. Generative models for simulating mobility trajectories. arXiv preprint arXiv:1811.12801 (2018).Google Scholar
- Mihee Lee, Samuel S Sohn, Seonghyeon Moon, Sejong Yoon, Mubbasir Kapadia, and Vladimir Pavlovic. 2022. Muse-VAE: multi-scale VAE for environment-aware long term trajectory prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2221--2230.Google ScholarCross Ref
- Yinfeng Li, Chen Gao, Xiaoyi Du, Huazhou Wei, Hengliang Luo, Depeng Jin, and Yong Li. 2022a. Automatically Discovering User Consumption Intents in Meituan. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3259--3269.Google ScholarDigital Library
- Yinfeng Li, Chen Gao, Xiaoyi Du, Huazhou Wei, Hengliang Luo, Depeng Jin, and Yong Li. 2022b. Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 1209--1218.Google ScholarDigital Library
- Yinfeng Li, Chen Gao, Quanming Yao, Tong Li, Depeng Jin, and Yong Li. 2022c. DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction. arXiv preprint arXiv:2208.06794 (2022).Google Scholar
- Kaikai Liu, Renjun Shuai, Li Ma, et al. 2021. Cells image generation method based on VAE-SGAN. Procedia Computer Science, Vol. 183 (2021), 589--595.Google ScholarCross Ref
- Yingtao Luo, Qiang Liu, and Zhaocheng Liu. 2021. Stan: Spatio-temporal attention network for next location recommendation. In Proceedings of the Web Conference 2021. 2177--2185.Google ScholarDigital Library
- Leandros A Maglaras and Dimitrios Katsaros. 2016. Social Clustering of Vehicles Based on Semi-Markov Processes. TVT, Vol. 65, 1 (2016), 318--332.Google ScholarCross Ref
- Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, and Greg Mori. 2019. A variational auto-encoder model for stochastic point processes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3165--3174.Google ScholarCross Ref
- Hongyuan Mei and Jason M Eisner. 2017. The neural hawkes process: A neurally self-modulating multivariate point process. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- Apollinaire Nadembega, Abdelhakim Hafid, and Tarik Taleb. 2014. Mobility-prediction-aware bandwidth reservation scheme for mobile networks. IEEE Transactions on Vehicular Technology, Vol. 64, 6 (2014), 2561--2576.Google ScholarCross Ref
- Zhen Pan, Zhenya Huang, Defu Lian, and Enhong Chen. 2020. A variational point process model for social event sequences. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 173--180.Google ScholarCross Ref
- Dimitrios Rafailidis and Fabio Crestani. 2018. Friend recommendation in location-based social networks via deep pairwise learning. In 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). 421--428.Google ScholarDigital Library
- Suman Ravuri, Karel Lenc, Matthew Willson, Dmitry Kangin, Remi Lam, Piotr Mirowski, Megan Fitzsimons, Maria Athanassiadou, Sheleem Kashem, Sam Madge, et al. 2021. Skilful precipitation nowcasting using deep generative models of radar. Nature, Vol. 597, 7878 (2021), 672--677.Google Scholar
- Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff, Rex Ying, Jure Leskovec, and Peter Battaglia. 2020. Learning to simulate complex physics with graph networks. In International Conference on Machine Learning. 8459--8468.Google Scholar
- Chaoming Song, Tal Koren, Pu Wang, and Albert-László Barabási. 2010. Modelling the scaling properties of human mobility. Nature Physics, Vol. 6, 10 (2010), 818--823.Google ScholarCross Ref
- Ha Yoon Song, Moo Sang Baek, and Minsuk Sung. 2019. Generating Human Mobility Route Based on Generative Adversarial Network. In Proc. FedCSIS.Google ScholarCross Ref
- Simon Suo, Sebastian Regalado, Sergio Casas, and Raquel Urtasun. 2021. Trafficsim: Learning to simulate realistic multi-agent behaviors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10400--10409.Google ScholarCross Ref
- Jakub M Tomczak. 2022. Why Deep Generative Modeling? In Deep Generative Modeling. 1--12.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proc. NeurISP.Google Scholar
- Jinzhong Wang, Xiangjie Kong, Azizur Rahim, Feng Xia, Amr Tolba, and Zafer Al-Makhadmeh. 2017. IS2Fun: Identification of subway station functions using massive urban data. IEEE Access, Vol. 5 (2017), 27103--27113.Google ScholarCross Ref
- Weiqing Wang, Hongzhi Yin, Xingzhong Du, Quoc Viet Hung Nguyen, and Xiaofang Zhou. 2018. TPM: A Temporal Personalized Model for Spatial Item Recommendation. ACM Trans. Intell. Syst. Technol., Vol. 9, 6 (2018).Google ScholarDigital Library
- Xiaofei Wang, Min Chen, Tarik Taleb, Adlen Ksentini, and Victor CM Leung. 2014. Cache in the air: Exploiting content caching and delivery techniques for 5G systems. IEEE Communications Magazine, Vol. 52, 2 (2014), 131--139.Google ScholarCross Ref
- Fei Wu, Hongjian Wang, and Zhenhui Li. 2016. Interpreting traffic dynamics using ubiquitous urban data. Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (2016), 69.Google ScholarDigital Library
- Weichang Wu, Junchi Yan, Xiaokang Yang, and Hongyuan Zha. 2018. Decoupled learning for factorial marked temporal point processes. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2516--2525.Google ScholarDigital Library
- Dongbo Xi, Fuzhen Zhuang, Yanchi Liu, Jingjing Gu, Hui Xiong, and Qing He. 2019. Modelling of bi-directional spatio-temporal dependence and users' dynamic preferences for missing poi check-in identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 5458--5465.Google ScholarDigital Library
- Quan Yuan, Gao Cong, Kaiqi Zhao, Zongyang Ma, and Aixin Sun. 2015. Who, where, when, and what: A nonparametric bayesian approach to context-aware recommendation and search for twitter users. ACM Transactions on Information Systems (TOIS), Vol. 33, 1 (2015).Google ScholarDigital Library
- Yuan Yuan, Jingtao Ding, Chenyang Shao, Depeng Jin, and Yong Li. 2023 a. Spatio-temporal Diffusion Point Processes. arXiv preprint arXiv:2305.12403 (2023).Google Scholar
- Yuan Yuan, Jingtao Ding, Huandong Wang, Depeng Jin, and Yong Li. 2022. Activity Trajectory Generation via Modeling Spatiotemporal Dynamics. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4752--4762.Google ScholarDigital Library
- Yuan Yuan, Huandong Wang, Jingtao Ding, Depeng Jin, and Yong Li. 2023 b. Learning to Simulate Daily Activities via Modeling Dynamic Human Needs. In Proceedings of the ACM Web Conference 2023. 906--916.Google ScholarDigital Library
- Paul A Zandbergen. 2014. Ensuring confidentiality of geocoded health data: assessing geographic masking strategies for individual-level data. Advances in medicine, Vol. 2014 (2014).Google Scholar
Index Terms
- Practical Synthetic Human Trajectories Generation Based on Variational Point Processes
Recommendations
Learning to Simulate Human Mobility
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningRealistic simulation of a massive amount of human mobility data is of great use in epidemic spreading modeling and related health policy-making. Existing solutions for mobility simulation can be classified into two categories: model-based methods and ...
Synthesizing Human Trajectories Based on Variational Point Processes
Synthesized human trajectories are instrumental for a large number of applications. However, existing trajectory synthesizing models are limited in either modeling variable-length trajectories with continuous temporal distribution or incorporating multi-...
Disk-Based Indexing of Recent Trajectories
The plethora of location-aware devices has led to countless location-based services in which huge amounts of spatiotemporal data get created every day. Several applications require efficient processing of queries on the locations of moving objects over ...
Comments