EUVIMEDEUVIMED entdecken
Crossref

RED: Effective Trajectory Representation Learning with Comprehensive Information

Silin Zhou, Shuo Shang, Lisi Chen, Christian S. Jensen, Panos Kalnis

Proceedings of the VLDB Endowment · 2024-10 · 18 (2) · 80-92

DOI: 10.14778/3705829.3705830 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 28.02.2025. Verfasst von Silin Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing TRL methods often produce vectors that, when used in downstream tasks, yield insufficiently accurate results. A key reason is that they fail to utilize the comprehensive information encompassed by trajectories. We propose a self-supervised TRL framework, called RED, which effectively exploits multiple types of trajectory information. Overall, RED adopts the Transformer as the backbone model and masks the constituting paths in trajectories to train a masked autoencoder (MAE). In particular, RED considers the moving patterns of trajectories by employing a R oad-aware masking strategy that retains key paths of trajectories during masking, thereby preserving crucial information of the trajectories. RED also adopts a spatial-temporal-user joint E mbedding scheme to encode comprehensive information when preparing the trajectories as model inputs. To conduct training, RED adopts D ual-objective task learning : the Transformer encoder predicts the next segment in a trajectory, and the Transformer decoder reconstructs the entire trajectory. RED also considers the spatial-temporal correlations of trajectories by modifying the attention mechanism of the Transformer. We compare RED with 9 state-of-the-art TRL methods for 4 downstream tasks on 3 real-world datasets, finding that RED can usually improve the accuracy of the best-performing baseline by over 5%.

Zitieren

APA

Zhou, S., Shang, S., Chen, L., Jensen, C. S., & Kalnis, P. (2024). RED: Effective Trajectory Representation Learning with Comprehensive Information. Proceedings of the VLDB Endowment, 18(2), 80-92. https://doi.org/10.14778/3705829.3705830

Vancouver

Zhou S, Shang S, Chen L, Jensen CS, Kalnis P. RED: Effective Trajectory Representation Learning with Comprehensive Information. Proceedings of the VLDB Endowment. 2024;18(2):80-92. doi:10.14778/3705829.3705830

BibTeX
@article{Zhou2024,
  author = {Zhou, Silin and Shang, Shuo and Chen, Lisi and Jensen, Christian S. and Kalnis, Panos},
  title = {RED: Effective Trajectory Representation Learning with Comprehensive Information},
  journal = {Proceedings of the VLDB Endowment},
  year = {2024},
  volume = {18},
  number = {2},
  pages = {80--92},
  doi = {10.14778/3705829.3705830}
}
Kostenlos starten →