EUVIMEDEUVIMED entdecken
Crossref

MH-GIN: Multi-Scale Heterogeneous Graph-Based Imputation Network for AIS Data

Hengyu Liu, Tianyi Li, Yuqiang He, Kristian Torp, Yushuai Li, Christian S. Jensen

Proceedings of the VLDB Endowment · 01.10.2025 · 19 (2) · 170-182

DOI: 10.14778/3773749.3773756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 17.03.2026. Verfasst von Hengyu Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 56 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Location-tracking data from the Automatic Identification System, much of which is publicly available, plays a key role in a range of maritime safety and monitoring applications. However, the data suffers from missing values that hamper downstream applications. Imputing the missing values is challenging because the values of different heterogeneous attributes are updated at diverse rates, resulting in the occurrence of multi-scale dependencies among attributes. Existing imputation methods that assume similar update rates across attributes are unable to capture and exploit such dependencies, limiting their imputation accuracy. We propose MH-GIN, a Multi-scale Heterogeneous Graph-based Imputation Network that aims improve imputation accuracy by capturing multi-scale dependencies. Specifically, MH-GIN first extracts multi-scale temporal features for each attribute while preserving their intrinsic heterogeneous characteristics. Then, it constructs a multi-scale heterogeneous graph to explicitly model dependencies between heterogeneous attributes to enable more accurate imputation of missing values through graph propagation. Experimental results on two real-world datasets find that MH-GIN is capable of an average 57% reduction in imputation errors compared to state-of-the-art methods, while maintaining computational efficiency.

Zitieren

APA

Liu, H., Li, T., He, Y., Torp, K., Li, Y., & Jensen, C. S. (2025). MH-GIN: Multi-Scale Heterogeneous Graph-Based Imputation Network for AIS Data. Proceedings of the VLDB Endowment, 19(2), 170-182. https://doi.org/10.14778/3773749.3773756

Vancouver

Liu H, Li T, He Y, Torp K, Li Y, Jensen CS. MH-GIN: Multi-Scale Heterogeneous Graph-Based Imputation Network for AIS Data. Proceedings of the VLDB Endowment. 2025;19(2):170-182. doi:10.14778/3773749.3773756

BibTeX
@article{Liu2025,
  author = {Liu, Hengyu and Li, Tianyi and He, Yuqiang and Torp, Kristian and Li, Yushuai and Jensen, Christian S.},
  title = {MH-GIN: Multi-Scale Heterogeneous Graph-Based Imputation Network for AIS Data},
  journal = {Proceedings of the VLDB Endowment},
  year = {2025},
  volume = {19},
  number = {2},
  pages = {170--182},
  doi = {10.14778/3773749.3773756}
}
Kostenlos starten →