Research

Paper

TESTING March 25, 2026

Hierarchical Spatial-Temporal Graph-Enhanced Model for Map-Matching

Authors

Anjun Gao, Zhenglin Wan, Pingfu Chao, Shunyu Yao

Abstract

The integration of GNSS data into portable devices has led to the generation of vast amounts of trajectory data, which is crucial for applications such as map-matching. To tackle the limitations of rule-based methods, recent works in deep learning for trajectory-related tasks occur. However, existing models remain challenging due to issues such as the difficulty of large-scale data labeling, ineffective modeling of spatial-temporal relationships, and discrepancies between training and test data distributions. To tackle these challenges, we propose HSTGMatch, a novel model designed to enhance map-matching performance. Our approach involves a two-stage process: hierarchical self-supervised learning and spatial-temporal supervised learning. We introduce a hierarchical trajectory representation, leveraging both grid cells and geographic tuples to capture moving patterns effectively. The model constructs an Adaptive Trajectory Adjacency Graph to dynamically capture spatial relationships, optimizing GATs for improved efficiency. Furthermore, we incorporate a Spatial-Temporal Factor to extract relevant features and employ a decay coefficient to address variations in trajectory length. Our extensive experiments demonstrate the model's superior performance, module effectiveness, and robustness, providing a promising solution for overcoming the existing limitations in map-matching applications. The source code of HSTGMatch is publicly available on GitHub at https://github.com/Nerooo-g/HSTGMatch.

Metadata

arXiv ID: 2603.24054
Provider: ARXIV
Primary Category: cs.DB
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24054v1</id>\n    <title>Hierarchical Spatial-Temporal Graph-Enhanced Model for Map-Matching</title>\n    <updated>2026-03-25T08:01:13Z</updated>\n    <link href='https://arxiv.org/abs/2603.24054v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24054v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The integration of GNSS data into portable devices has led to the generation of vast amounts of trajectory data, which is crucial for applications such as map-matching. To tackle the limitations of rule-based methods, recent works in deep learning for trajectory-related tasks occur. However, existing models remain challenging due to issues such as the difficulty of large-scale data labeling, ineffective modeling of spatial-temporal relationships, and discrepancies between training and test data distributions. To tackle these challenges, we propose HSTGMatch, a novel model designed to enhance map-matching performance. Our approach involves a two-stage process: hierarchical self-supervised learning and spatial-temporal supervised learning. We introduce a hierarchical trajectory representation, leveraging both grid cells and geographic tuples to capture moving patterns effectively. The model constructs an Adaptive Trajectory Adjacency Graph to dynamically capture spatial relationships, optimizing GATs for improved efficiency. Furthermore, we incorporate a Spatial-Temporal Factor to extract relevant features and employ a decay coefficient to address variations in trajectory length. Our extensive experiments demonstrate the model's superior performance, module effectiveness, and robustness, providing a promising solution for overcoming the existing limitations in map-matching applications. The source code of HSTGMatch is publicly available on GitHub at https://github.com/Nerooo-g/HSTGMatch.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DB'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-25T08:01:13Z</published>\n    <arxiv:primary_category term='cs.DB'/>\n    <arxiv:journal_ref>Gao, A., Wan, Z., Chao, P., Yao, S. (2025). Hierarchical Spatial-Temporal Graph-Enhanced Model for Map-Matching. In: Databases Theory and Applications. ADC 2024. Lecture Notes in Computer Science, vol 15449. Springer, Singapore</arxiv:journal_ref>\n    <author>\n      <name>Anjun Gao</name>\n    </author>\n    <author>\n      <name>Zhenglin Wan</name>\n    </author>\n    <author>\n      <name>Pingfu Chao</name>\n    </author>\n    <author>\n      <name>Shunyu Yao</name>\n    </author>\n    <arxiv:doi>10.1007/978-981-96-1242-0_4</arxiv:doi>\n    <link href='https://doi.org/10.1007/978-981-96-1242-0_4' rel='related' title='doi'/>\n  </entry>"
}