Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics (2211.09510v4)

Published 17 Nov 2022 in cs.LG

Abstract: Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various downstream tasks, such as trajectory classification, clustering, and similarity computation. Existing TRL works usually treat trajectories as ordinary sequence data, while some important spatial-temporal characteristics, such as temporal regularities and travel semantics, are not fully exploited. To fill this gap, we propose a novel Self-supervised trajectory representation learning framework with TemporAl Regularities and Travel semantics, namely START. The proposed method consists of two stages. The first stage is a Trajectory Pattern-Enhanced Graph Attention Network (TPE-GAT), which converts the road network features and travel semantics into representation vectors of road segments. The second stage is a Time-Aware Trajectory Encoder (TAT-Enc), which encodes representation vectors of road segments in the same trajectory as a trajectory representation vector, meanwhile incorporating temporal regularities with the trajectory representation. Moreover, we also design two self-supervised tasks, i.e., span-masked trajectory recovery and trajectory contrastive learning, to introduce spatial-temporal characteristics of trajectories into the training process of our START framework. The effectiveness of the proposed method is verified by extensive experiments on two large-scale real-world datasets for three downstream tasks. The experiments also demonstrate that our method can be transferred across different cities to adapt heterogeneous trajectory datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Z. Fang, L. Pan, L. Chen, Y. Du, and Y. Gao, “MDTP: A multi-source deep traffic prediction framework over spatio-temporal trajectory data,” Proc. VLDB Endow., vol. 14, no. 8, pp. 1289–1297, 2021.
  2. J. Wang, N. Wu, W. X. Zhao, F. Peng, and X. Lin, “Empowering a* search algorithms with neural networks for personalized route recommendation,” in KDD.   ACM, 2019, pp. 539–547.
  3. J. Wang, J. Jiang, W. Jiang, C. Li, and W. X. Zhao, “Libcity: An open library for traffic prediction,” in SIGSPATIAL/GIS.   ACM, 2021, pp. 145–148.
  4. J. Ji, J. Wang, Z. Jiang, J. Jiang, and H. Zhang, “STDEN: towards physics-guided neural networks for traffic flow prediction,” in AAAI.   AAAI Press, 2022, pp. 4048–4056.
  5. J. Wang, X. Lin, Y. Zuo, and J. Wu, “Dgeye: Probabilistic risk perception and prediction for urban dangerous goods management,” ACM Trans. Inf. Syst., vol. 39, no. 3, pp. 28:1–28:30, 2021.
  6. G. Li, C. Hung, M. Liu, L. Pan, W. Peng, and S. G. Chan, “Spatial-temporal similarity for trajectories with location noise and sporadic sampling,” in 37th IEEE International Conference on Data Engineering, (ICDE), Chania, Greece, April 19-22, 2021.   IEEE, 2021, pp. 1224–1235.
  7. T.-Y. Fu and W.-C. Lee, “Trembr: Exploring road networks for trajectory representation learning,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 11, no. 1, pp. 1–25, 2020.
  8. X. Li, K. Zhao, G. Cong, C. S. Jensen, and W. Wei, “Deep representation learning for trajectory similarity computation,” in 34th IEEE International Conference on Data Engineering, (ICDE), Paris, France, April 16-19, 2018.   IEEE Computer Society, 2018, pp. 617–628.
  9. D. Yao, C. Zhang, Z. Zhu, J. Huang, and J. Bi, “Trajectory clustering via deep representation learning,” in 2017 international joint conference on neural networks (IJCNN).   IEEE, 2017, pp. 3880–3887.
  10. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
  11. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  12. D. Yao, G. Cong, C. Zhang, and J. Bi, “Computing trajectory similarity in linear time: A generic seed-guided neural metric learning approach,” in 35th IEEE International Conference on Data Engineering, (ICDE), Macao, China, April 8-11, 2019.   IEEE, 2019, pp. 1358–1369.
  13. P. Yang, H. Wang, Y. Zhang, L. Qin, W. Zhang, and X. Lin, “T3S: effective representation learning for trajectory similarity computation,” in 37th IEEE International Conference on Data Engineering, (ICDE), Chania, Greece, April 19-22, 2021.   IEEE, 2021, pp. 2183–2188.
  14. Z. Fang, Y. Du, L. Chen, Y. Hu, Y. Gao, and G. Chen, “E22{}^{\mbox{2}}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTdtc: An end to end deep trajectory clustering framework via self-training,” in 37th IEEE International Conference on Data Engineering, (ICDE), Chania, Greece, April 19-22, 2021.   IEEE, 2021, pp. 696–707.
  15. Y. Liu, K. Zhao, G. Cong, and Z. Bao, “Online anomalous trajectory detection with deep generative sequence modeling,” in 36th IEEE International Conference on Data Engineering, (ICDE), Dallas, TX, USA, April 20-24, 2020.   IEEE, 2020, pp. 949–960.
  16. S. B. Yang and B. Yang, “Learning to rank paths in spatial networks,” in 36th IEEE International Conference on Data Engineering, (ICDE), Dallas, TX, USA, April 20-24, 2020.   IEEE, 2020, pp. 2006–2009.
  17. Y. Chen, X. Li, G. Cong, Z. Bao, C. Long, Y. Liu, A. K. Chandran, and R. Ellison, “Robust road network representation learning: When traffic patterns meet traveling semantics,” in CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management.   ACM, 2021, pp. 211–220.
  18. S. B. Yang, C. Guo, J. Hu, J. Tang, and B. Yang, “Unsupervised path representation learning with curriculum negative sampling,” in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021.   ijcai.org, 2021, pp. 3286–3292.
  19. A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in KDD.   ACM, 2016, pp. 855–864.
  20. P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph attention networks,” CoRR, vol. abs/1710.10903, 2017.
  21. C. Yang and G. Gidofalvi, “Fast map matching, an algorithm integrating hidden markov model with precomputation,” International Journal of Geographical Information Science, vol. 32, no. 3, pp. 547–570, 2018.
  22. J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers for language understanding,” in NAACL-HLT (1).   Association for Computational Linguistics, 2019, pp. 4171–4186.
  23. T. Gao, X. Yao, and D. Chen, “Simcse: Simple contrastive learning of sentence embeddings,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021.   Association for Computational Linguistics, 2021, pp. 6894–6910.
  24. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” in International conference on machine learning.   PMLR, 2020, pp. 1597–1607.
  25. OpenStreetMap contributors, “Planet dump retrieved from https://planet.osm.org ,” https://www.openstreetmap.org, 2017.
  26. H. Zhang, X. Zhang, Q. Jiang, B. Zheng, Z. Sun, W. Sun, and C. Wang, “Trajectory similarity learning with auxiliary supervision and optimal matching,” in Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020.   ijcai.org, 2020, pp. 3209–3215.
  27. M. Yue, Y. Li, H. Yang, R. Ahuja, Y. Chiang, and C. Shahabi, “DETECT: deep trajectory clustering for mobility-behavior analysis,” in 2019 IEEE International Conference on Big Data (IEEE BigData), Los Angeles, CA, USA, December 9-12, 2019.   IEEE, 2019, pp. 988–997.
  28. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
  29. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019.   OpenReview.net, 2019.
  30. J. Y. Yen, “Finding the k shortest loopless paths in a network,” management Science, vol. 17, no. 11, pp. 712–716, 1971.
  31. J. Gao, D. He, X. Tan, T. Qin, L. Wang, and T. Liu, “Representation degeneration problem in training natural language generation models,” in 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019.   OpenReview.net, 2019.
  32. B. Yi, H. V. Jagadish, and C. Faloutsos, “Efficient retrieval of similar time sequences under time warping,” in Proceedings of the Fourteenth International Conference on Data Engineering (ICDE), Orlando, Florida, USA, February 23-27, 1998.   IEEE Computer Society, 1998, pp. 201–208.
  33. M. Vlachos, D. Gunopulos, and G. Kollios, “Discovering similar multidimensional trajectories,” in Proceedings of the 18th International Conference on Data Engineering (ICDE), San Jose, CA, USA, February 26 - March 1, 2002.   IEEE Computer Society, 2002, pp. 673–684.
  34. H. Alt and M. Godau, “Computing the fréchet distance between two polygonal curves,” International Journal of Computational Geometry & Applications, vol. 5, no. 01n02, pp. 75–91, 1995.
  35. L. Chen, M. T. Özsu, and V. Oria, “Robust and fast similarity search for moving object trajectories,” in Proceedings of the 2005 ACM SIGMOD international conference on Management of data, 2005, pp. 491–502.
  36. F. Zhou, H. Wu, G. Trajcevski, A. Khokhar, and K. Zhang, “Semi-supervised trajectory understanding with poi attention for end-to-end trip recommendation,” ACM Transactions on Spatial Algorithms and Systems (TSAS), vol. 6, no. 2, pp. 1–25, 2020.
  37. F. Zhou, P. Wang, X. Xu, W. Tai, and G. Trajcevski, “Contrastive trajectory learning for tour recommendation,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 13, no. 1, pp. 1–25, 2021.
  38. Q. Gao, W. Wang, K. Zhang, X. Yang, C. Miao, and T. Li, “Self-supervised representation learning for trip recommendation,” Knowledge-Based Systems, vol. 247, p. 108791, 2022.
  39. Y. Yan, R. Li, S. Wang, F. Zhang, W. Wu, and W. Xu, “Consert: A contrastive framework for self-supervised sentence representation transfer,” in ACL/IJCNLP (1).   Association for Computational Linguistics, 2021, pp. 5065–5075.
  40. N. Wu, W. X. Zhao, J. Wang, and D. Pan, “Learning effective road network representation with hierarchical graph neural networks,” in KDD.   ACM, 2020, pp. 6–14.
  41. X. Wang, P. Cui, J. Wang, J. Pei, W. Zhu, and S. Yang, “Community preserving network embedding,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
  42. J. Yu, H. Yin, X. Xia, T. Chen, J. Li, and Z. Huang, “Self-supervised learning for recommender systems: A survey,” CoRR, vol. abs/2203.15876, 2022.
Citations (50)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now