MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data
Summary: MH-GIN models AIS attributes’ heterogeneous update rates via multi-scale temporal features and a multi-scale heterogeneous graph for dependency-aware imputation. It reduces errors by 57% on two real datasets while retaining computational efficiency. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hengyu Liu (Aalborg University)
- 2. Tianyi Li (Aalborg University)
- 3. Yuqiang He (Guangxi University)
- 4. Kristian Torp (Aalborg University)
- 5. Yushuai Li (Aalborg University)
- 6. Christian S. Jensen (Aalborg University)
BibTeX Citation
@article{liu_vldb26,
title = {{MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data}},
author = {Liu, Hengyu and Li, Tianyi and He, Yuqiang and Torp, Kristian and Li, Yushuai and Jensen, Christian S.},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {2},
pages = {170--182},
doi = {10.14778/3773749.3773756},
url = {https://doi.org/10.14778/3773749.3773756},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,545 | Mind the Gap: An Experimental Evaluation of Imputation of Missing Values Techniques in Time Series | 2020 | VLDB | 8.4401333e-05 |
| 4,034 | Missing Value Imputation on Multidimensional Time Series | 2021 | VLDB | 6.9446462e-05 |
| 6,002 | Compression of Uncertain Trajectories in Road Networks | 2020 | VLDB | 6.0133202e-05 |
| 7,505 | Kamel: A Scalable BERT-based System for Trajectory Imputation | 2024 | VLDB | 5.6029996e-05 |
| 7,813 | TRACE: Real-time Compression of Streaming Trajectories in Road Networks | 2021 | VLDB | 5.5390003e-05 |
| 8,727 | Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification | 2025 | VLDB | 5.3766157e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,390 | ImputeVIS: An Interactive Evaluator to Benchmark Imputation Techniques for Time Series Data | 2024 | VLDB |
| 2 | 10,924 | On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing | 2025 | VLDB |
| 3 | 11,082 | MSGNN: Masked Schema based Graph Neural Networks | 2025 | VLDB |
| 4 | 8,010 | Nuhuo: An Effective Estimation Model for Traffic Speed Histogram Imputation on A Road Network | 2024 | VLDB |
| 5 | 3,386 | Efficient and Effective Data Imputation with Influence Functions | 2022 | VLDB |
| 6 | 4,034 | Missing Value Imputation on Multidimensional Time Series | 2021 | VLDB |
| 7 | 6,642 | Missing Data Imputation with Uncertainty-Driven Network | 2024 | SIGMOD |
| 8 | 13,384 | Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Photovoltaic Data Imputation | 2023 | SIGMOD |
| 9 | 5,702 | DAMR: Dynamic Adjacency Matrix Representation Learning for Multivariate Time Series Imputation | 2023 | SIGMOD |
| 10 | 7,844 | Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation | 2024 | VLDB |