ABSTRACT
Trajectory-User Linking (TUL) aiming to identify users of anonymous trajectories, has recently received increasing attention due to its wide range of applications, such as criminal investigation and personalized recommendation systems. In this paper, we propose a flexible <u>S</u>emi-<u>S</u>upervised framework for <u>T</u>rajectory-<u>U</u>ser <u>L</u>inking, namely S2TUL, which includes five components: trajectory-level graph construction, trajectory relation modeling, location-level sequential modeling, a classification layer and greedy trajectory-user relinking. The first two components are proposed to model the relationships among trajectories, in which three homogeneous graphs and two heterogeneous graphs are firstly constructed and then delivered into the graph convolutional networks for converting the discrete identities to hidden representations. Since the graph constructions are irrelevant to the corresponding users, the unlabelled trajectories can also be included in the graphs, which enables the framework to be trained in a semi-supervised way. Afterwards, the location-level sequential modeling component is designed to capture fine-grained intra-trajectory information by passing the trajectories into the sequential neural networks. Finally, these two level representations are concatenated into a classification layer to predict the user of the input trajectory. In the testing phase, a greedy trajectory-user relinking method is proposed to assure the linking results satisfy the timespan overlap constraint. We conduct extensive experiments on three public datasets with six representative competitors. The evaluation results demonstrate the effectiveness of the proposed framework.
Supplemental Material
- Meng Chen, Yan Zhao, Yang P. Liu, Xiaohui Yu, and Kai Zheng. 2020. Modeling Spatial Trajectories with Attribute Representation Learning. TKDE (2020), 1--1.Google Scholar
- Eunjoon Cho, Seth A. Myers, and Jure Leskovec. 2011. Friendship and mobility: user movement in location-based social networks. In KDD. 1082--1090.Google Scholar
- Yue Cui, Hao Sun, Yan Zhao, Hongzhi Yin, and Kai Zheng. 2021. Sequential- Knowledge-Aware Next POI Recommendation: A Meta-Learning Approach. TIS (2021), 23:1--23:22.Google Scholar
- Liwei Deng, Hao Sun, Rui Sun, Yan Zhao, and Han Su. 2022. Efficient and Effective Similar Subtrajectory Search: A Spatial-aware Comprehension Approach. TIST 13, 3 (2022), 3511--3522.Google ScholarDigital Library
- Liwei Deng, Yan Zhao, Zidan Fu, Hao Sun, Shuncheng Liu, and Kai Zheng. 2022. Efficient Trajectory Similarity Computation with Contrastive Learning. In CIKM. 365--374.Google Scholar
- J. 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 Scholar
- Qiang Gao, Fan Zhou, Kunpeng Zhang, Goce Trajcevski, Xucheng Luo, and Fengli Zhang. 2017. Identifying Human Mobility via Trajectory Embeddings. In IJCAI. 1689--1695.Google Scholar
- Xiangnan He, Kuan Deng, Xiang Wang, Yaliang Li, Yongdong Zhang, and Meng Wang. 2020. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In SIGIR. 639--648.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9 (1997), 1735--1780.Google ScholarDigital Library
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. CoRR abs/1412.6980 (2015).Google Scholar
- Thomas Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. ArXiv abs/1609.02907 (2017).Google Scholar
- Xiucheng Li, Kaiqi Zhao, G. Cong, Christian S. Jensen, and Wei Wei. 2018. Deep Representation Learning for Trajectory Similarity Computation. In ICDE. 617-- 628.Google Scholar
- Shuncheng Liu, Han Su, Yan Zhao, Kai Zeng, and Kai Zheng. 2021. Lane Change Scheduling for Autonomous Vehicle: A Prediction-and-Search Framework. In KDD. 3343--3353.Google Scholar
- Congcong Miao, Jilong Wang, Heng Yu, Weicheng Zhang, and Yinyao Qi. 2020. Trajectory-User Linking with Attentive Recurrent Network. In AAMAS. 878--886.Google Scholar
- Tomas Mikolov, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In ICLR.Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In NIPS. 3111--3119.Google Scholar
- Dazhuo Qiu, Yihao Wang, Yan Zhao, Liwei Deng, and Kai Zheng. 2022. City- Cross: Transferring Attention-based Knowledge for Location-based Advertising Recommendation. In CIKM. 254--261.Google Scholar
- M. Schlichtkrull, Thomas Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convolutional Networks. ArXiv abs/1703.06103 (2018).Google Scholar
- Han Su, Guanglin Cong, Weihai Chen, Bolong Zheng, and Kai Zheng. 2019. Personalized Route Description Based On Historical Trajectories. In CIKM. 79-- 88.Google Scholar
- Huimin Sun, Jiajie Xu, Kai Zheng, Pengpeng Zhao, Pingfu Chao, and Xiaofang Zhou. 2021. MFNP: A Meta-optimized Model for Few-shot Next POI Recommendation. In IJCAI. 3017--3023.Google Scholar
- Hao Sun, Changjie Yang, Liwei Deng, Fan Zhou, Feiteng Huang, and Kai Zheng. 2021. PeriodicMove: Shift-aware Human Mobility Recovery with Graph Neural Network. In CIKM. 1734--1743.Google Scholar
- Rui Sun, Xuezhi Cao, Yan Zhao, Juncheng Wan, Kun Zhou, Fuzheng Zhang, Zhongyuan Wang, and Kai Zheng. 2020. Multi-modal Knowledge Graphs for Recommender Systems. In CIKM. 1405--1414.Google Scholar
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio', and Yoshua Bengio. 2018. Graph Attention Networks. ArXiv abs/1710.10903 (2018).Google Scholar
- 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 abs/2101.00646 (2021).Google Scholar
- Dingqi Yang, Daqing Zhang, Vincent Wenchen Zheng, and Zhiyong Yu. 2015. Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs. IEEE Transactions on Systems, Man, and Cybernetics: Systems 45 (2015), 129--142.Google ScholarCross Ref
- Jia-Ching Ying, Wang-Chien Lee, Tz-Chiao Weng, and Vincent S. Tseng. 2011. Semantic trajectory mining for location prediction. In SIGSPATIAL. 34--43.Google Scholar
- Kangzhi Zhao, Yong Zhang, Hongzhi Yin, Jin Wang, Kai Zheng, Xiaofang Zhou, and Chunxiao Xing. 2020. Discovering Subsequence Patterns for Next POI Recommendation. In IJCAI. 3216--3222.Google Scholar
- Pengpeng Zhao, Chengfeng Xu, Yanchi Liu, Victor S. Sheng, Kai Zheng, Hui Xiong, and Xiaofang Zhou. 2021. Photo2Trip: Exploiting Visual Contents in Geo-Tagged Photos for Personalized Tour Recommendation. TKDE 33 (2021), 1708--1721.Google ScholarDigital Library
- Yan Zhao, Shuo Shang, Yu Wang, Bolong Zheng, Quoc Viet Hung Nguyen, and Kai Zheng. 2018. REST: A Reference-based Framework for Spatio-temporal Trajectory Compression. In KDD. 2797--2806.Google Scholar
- Kai Zheng, Yan Zhao, Defu Lian, Bolong Zheng, Guanfeng Liu, and Xiaofang Zhou. 2020. Reference-Based Framework for Spatio-Temporal Trajectory Compression and Query Processing. TKDE 32 (2020), 2227--2240.Google ScholarCross Ref
- Fan Zhou, Shupei Chen, Jin Wu, Chengtai Cao, and Shengming Zhang. 2021. Trajectory-User Linking via Graph Neural Network. In ICC. 1--6.Google Scholar
- Fan Zhou, Qiang Gao, Goce Trajcevski, Kunpeng Zhang, Ting Zhong, and Fengli Zhang. 2018. Trajectory-User Linking via Variational AutoEncoder. In IJCAI. 3212--3218.Google Scholar
- Fan Zhou, Lei Liu, Kunpeng Zhang, Goce Trajcevski, Jin Wu, and Ting Zhong. 2018. DeepLink: A Deep Learning Approach for User Identity Linkage. In INFOCOM. 1313--1321.Google Scholar
- Fan Zhou, Xin Liu, Kunpeng Zhang, and Goce Trajcevski. 2021. Toward Discriminating and Synthesizing Motion Traces Using Deep Probabilistic Generative Models. TNNLS 32 (2021), 2401--2414.Google ScholarCross Ref
- 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
- S2TUL: A Semi-Supervised Framework for Trajectory-User Linking
Recommendations
Multi-task Adversarial Learning for Semi-supervised Trajectory-User Linking
Machine Learning and Knowledge Discovery in DatabasesAbstractTrajectory-User Linking (TUL), which aims to link the trajectories to the users who have generated them, is critically important to many real applications. Existing approaches generally consider TUL as a supervised learning problem which requires ...
A Survey of Semi-Supervised Learning Methods
CIS '08: Proceedings of the 2008 International Conference on Computational Intelligence and Security - Volume 02In traditional machine learning approaches to classification, one uses only a labelled set to train the classifier. Labelled instances however are often difficult, expensive, or time consuming to obtain, as they require the efforts of experienced human ...
CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
Computer Vision – ECCV 2022AbstractTo improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data. We show that these two approaches, at the two ...
Comments