Hao Sun
ABSTRACT
Human mobility recovery is of great importance for a wide range of location-based services. However, recovering human mobility is not trivial because of three challenges: 1) complex transition patterns among locations; 2) multi-level periodicity and shifting periodicity of human mobility; 3) sparsity of the collected trajectory data. In this paper, we propose PeriodicMove, a neural attention model based on graph neural network for human mobility recovery from lengthy and sparse trajectories. In PeriodicMove, we first construct a directed graph for each trajectory and capture complex location transition patterns using graph neural network. Then, we design two attention mechanisms which capture multi-level periodicity and shifting periodicity of human mobility respectively. Finally, a spatial-aware loss function is proposed to incorporate spatial proximity into the model optimization, which alleviates the data sparsity problem. We perform extensive experiments and the evaluation results demonstrate that PeriodicMove yields significant improvements over the competitors on two representative real-life mobility datasets. In addition, by providing high-quality mobility data, our model can benefit a variety of mobility-oriented downstream applications.
Supplemental Material
- Layth C Alwan and Harry V Roberts. 1988. Time-series modeling for statistical process control. Journal of business & economic statistics, Vol. 6, 1 (1988), 87--95.Google Scholar
- Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. 2018. Brits: Bidirectional recurrent imputation for time series. arXiv preprint arXiv:1805.10572 (2018).Google Scholar
- Guangshuo Chen, Aline Carneiro Viana, Marco Fiore, and Carlos Sarraute. 2019a. Complete trajectory reconstruction from sparse mobile phone data. EPJ Data Science, Vol. 8, 1 (2019), 30.Google ScholarCross Ref
- Meng Chen, Yan Zhao, Yang Liu, Xiaohui Yu, and Kai Zheng. 2020. Modeling spatial trajectories with attribute representation learning. TKDE (2020).Google Scholar
- Xu Chen, Yongfeng Zhang, and Zheng Qin. 2019b. Dynamic explainable recommendation based on neural attentive models. In AAAI, Vol. 33. 53--60.Google ScholarDigital Library
- Yue Cui, Hao Sun, Yan Zhao, Hongzhi Yin, and Kai Zheng. 2021. Sequential-knowledge-aware Next POI Recommendation: A Meta-learning Approach. TOIS (2021). Google ScholarDigital Library
- Liwei Deng, Hao Sun, Rui Sun, Yan Zhao, and Han Su. 2021. Efficient and Effective Similar Subtrajectory Search: A Spatial-aware Comprehension Approach. TIST (2021).Google Scholar
- David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael Gómez-Bombarelli, Timothy Hirzel, Alán Aspuru-Guzik, and Ryan P Adams. 2015. Convolutional networks on graphs for learning molecular fingerprints. arXiv preprint arXiv:1509.09292 (2015). Google ScholarDigital Library
- Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, and Depeng Jin. 2018. Deepmove: Predicting human mobility with attentional recurrent networks. In WWW. 1459--1468. Google ScholarDigital Library
- Sébastien Gambs, Marc-Olivier Killijian, and Miguel Núnez del Prado Cortez. 2012. Next place prediction using mobility markov chains. In Proceedings of the first workshop on measurement, privacy, and mobility. 1--6. Google ScholarDigital Library
- Aditya Grover and Jure Leskovec. 2016. Node2vec: Scalable feature learning for networks. In KDD. 855--864. Google ScholarDigital Library
- Ralf Hartmut Güting and Markus Schneider. 1995. Realm-based spatial data types: The ROSE algebra. The VLDB Journal, Vol. 4, 2 (1995), 243--286. Google ScholarDigital Library
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Dongsheng Li, Chao Chen, Qin Lv, Junchi Yan, Li Shang, and Stephen Chu. 2016. Low-rank matrix approximation with stability. In ICML. PMLR, 295--303. Google ScholarDigital Library
- Li Li, Yuebiao Li, and Zhiheng Li. 2013. Efficient missing data imputing for traffic flow by considering temporal and spatial dependence. Transportation research part C: emerging technologies, Vol. 34 (2013), 108--120.Google Scholar
- Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, and Sanja Fidler. 2017. Situation recognition with graph neural networks. In ICCV. 4173--4182.Google Scholar
- Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015).Google Scholar
- Zhongyang Li, Xiao Ding, and Ting Liu. 2018. Constructing narrative event evolutionary graph for script event prediction. arXiv preprint arXiv:1805.05081 (2018). Google ScholarDigital Library
- Qiang Liu, Shu Wu, Liang Wang, and Tieniu Tan. 2016. Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI, Vol. 30. Google ScholarDigital Library
- Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018).Google Scholar
- Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, and Xiaojie Yuan. 2018. Multivariate time series imputation with generative adversarial networks. In NIPS. 1603--1614. Google ScholarDigital Library
- Kenneth Marino, Ruslan Salakhutdinov, and Abhinav Gupta. 2016. The more you know: Using knowledge graphs for image classification. arXiv preprint arXiv:1612.04844 (2016).Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546 (2013).Google Scholar
- Andriy Mnih and Russ R Salakhutdinov. 2007. Probabilistic matrix factorization. NIPS, Vol. 20 (2007), 1257--1264. Google ScholarDigital Library
- Steffen Moritz and Thomas Bartz-Beielstein. 2017. imputeTS: time series missing value imputation in R. R J., Vol. 9, 1 (2017), 207.Google ScholarCross Ref
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019). Google ScholarDigital Library
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In KDD. 701--710. Google ScholarDigital Library
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks, Vol. 20, 1 (2008), 61--80. Google ScholarDigital Library
- Hao Sun, Zijian Wu, Yue Cui, Liwei Deng, Yan Zhao, and Kai Zheng. 2021. Personalized Dynamic Knowledge-Aware Recommendation with Hybrid Explanations. In DASFAA. 148--164.Google Scholar
- Ke Sun, Tieyun Qian, Tong Chen, Yile Liang, Quoc Viet Hung Nguyen, and Hongzhi Yin. 2020. Where to go next: Modeling long-and short-term user preferences for point-of-interest recommendation. In AAAI, Vol. 34. 214--221.Google ScholarCross Ref
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. Line: Large-scale information network embedding. In WWW. 1067--1077. Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017).Google Scholar
- Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Jingyuan Wang, Ning Wu, Xinxi Lu, Xin Zhao, and Kai Feng. 2019. Deep trajectory recovery with fine-grained calibration using Kalman filter. TKDE (2019).Google Scholar
- Zheng Wang, Cheng Long, Gao Cong, and Yiding Liu. 2020. Efficient and effective similar subtrajectory search with deep reinforcement learning. arXiv preprint arXiv:2003.02542 (2020).Google Scholar
- Fei Wu and Zhenhui Li. 2016. Where did you go: Personalized annotation of mobility records. In CIKM. 589--598. Google ScholarDigital Library
- Fei Wu, Zhenhui Li, Wang-Chien Lee, Hongjian Wang, and Zhuojie Huang. 2015. Semantic annotation of mobility data using social media. In WWW. 1253--1263. Google ScholarDigital Library
- Shu Wu, Yuyuan Tang, Yanqiao Zhu, Liang Wang, Xing Xie, and Tieniu Tan. 2019. Session-based recommendation with graph neural networks. In AAAI, Vol. 33. 346--353.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 AAAI, Vol. 33. 5458--5465.Google ScholarDigital Library
- Tong Xia, Yunhan Qi, Jie Feng, Fengli Xu, Funing Sun, Diansheng Guo, and Yong Li. 2021. AttnMove: History Enhanced Trajectory Recovery via Attentional Network. arXiv preprint arXiv:2101.00646 (2021).Google Scholar
- Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Victor S Sheng, Jiajie Xu, Fuzhen Zhuang, Junhua Fang, and Xiaofang Zhou. 2019. Graph Contextualized Self-Attention Network for Session-based Recommendation. In IJCAI, Vol. 19. 3940--3946. Google ScholarDigital Library
- Dingqi Yang, Daqing Zhang, Vincent W Zheng, and Zhiyong Yu. 2014. Modeling user activity preference by leveraging user spatial temporal characteristics in LBSNs. IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 45, 1 (2014), 129--142.Google ScholarCross Ref
- Yongfeng Zhang, Qingyao Ai, Xu Chen, and W Bruce Croft. 2017. Joint representation learning for top-n recommendation with heterogeneous information sources. In CIKM. 1449--1458. Google ScholarDigital Library
- Jing Zhao, Jiajie Xu, Rui Zhou, Pengpeng Zhao, Chengfei Liu, and Feng Zhu. 2018b. On prediction of user destination by sub-trajectory understanding: A deep learning based approach. In CIKM. 1413--1422. Google ScholarDigital Library
- Yan Zhao, Shuo Shang, Yu Wang, Bolong Zheng, Quoc Viet Hung Nguyen, and Kai Zheng. 2018a. Rest: A reference-based framework for spatio-temporal trajectory compression. In SIGKDD. 2797--2806. Google ScholarDigital Library
- Kai Zheng, Yan Zhao, Defu Lian, Bolong Zheng, Guanfeng Liu, and Xiaofang Zhou. 2019. Reference-based framework for spatio-temporal trajectory compression and query processing. TKDE, Vol. 32, 11 (2019), 2227--2240.Google ScholarCross Ref
- Yu Zheng, Licia Capra, Ouri Wolfson, and Hai Yang. 2014. Urban computing: concepts, methodologies, and applications. TIST, Vol. 5, 3 (2014), 1--55. Google ScholarDigital Library
- Yu Zheng, Quannan Li, Yukun Chen, Xing Xie, and Wei-Ying Ma. 2008. Understanding mobility based on GPS data. In UbiComp. 312--321. Google ScholarDigital Library
- Yu Zheng, Xing Xie, and Wei-Ying Ma. 2010. Geolife: A collaborative social networking service among user, location and trajectory. IEEE Data Eng. Bull., Vol. 33, 2 (2010), 32--39.Google Scholar
- Yu Zheng, Lizhu Zhang, Xing Xie, and Wei-Ying Ma. 2009. Mining interesting locations and travel sequences from GPS trajectories. In WWW. 791--800. Google ScholarDigital Library
- Hao Zhou, Yan Zhao, Junhua Fang, Xuanhao Chen, and Kai Zeng. 2019. Hybrid route recommendation with taxi and shared bicycles. Distributed and Parallel Databases (2019), 1--21.Google Scholar
Index Terms
- PeriodicMove: Shift-aware Human Mobility Recovery with Graph Neural Network
Recommendations
DeepMove: Predicting Human Mobility with Attentional Recurrent Networks
WWW '18: Proceedings of the 2018 World Wide Web ConferenceHuman mobility prediction is of great importance for a wide spectrum of location-based applications. However, predicting mobility is not trivial because of three challenges: 1) the complex sequential transition regularities exhibited with time-dependent ...
Batch and negative sampling design for human mobility graph neural network training
HuMob-Challenge '23: Proceedings of the 1st International Workshop on the Human Mobility Prediction ChallengeThis study presents a deep learning approach to human mobility prediction within a network science framework. We proposed a human mobility graph that defines two types of nodes---people and locations---and employs domain-specific attributes to capture ...
Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
SIGSPATIAL '23: Proceedings of the 31st ACM International Conference on Advances in Geographic Information SystemsNext Point-of-Interest (POI) recommendation plays a crucial role in urban mobility applications. Recently, POI recommendation models based on Graph Neural Networks (GNN) have been extensively studied and achieved, however, the effective incorporation ...
Comments