MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version)

2025-07-27

AI Summary

AIS trajectory data exhibit heterogeneous attribute update frequencies, leading to complex multiscale dependencies; existing imputation methods—assuming uniform update rates across attributes—fail to accurately model such heterogeneity, thereby degrading imputation accuracy. To address this, we propose a graph neural network–based imputation method explicitly designed for multiscale heterogeneous dependencies. Our approach introduces, for the first time, a multiscale heterogeneous graph structure that jointly encodes temporal and semantic dependencies among attributes with distinct update frequencies. It integrates multiscale temporal feature extraction, heterogeneous graph construction, and adaptive graph propagation to jointly model attribute heterogeneity and dynamic temporal patterns. Evaluated on two real-world AIS datasets, our method reduces average imputation error by 57% over state-of-the-art baselines while maintaining favorable computational efficiency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

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. The source code and implementation details of MH-GIN are publicly available https://github.com/hyLiu1994/MH-GIN.

Problem

• Imputing missing values in maritime AIS tracking data
• Handling multi-scale dependencies among heterogeneous attributes
• Improving accuracy over methods assuming uniform update rates

Innovation

• Extracts multi-scale temporal features for attributes
• Constructs multi-scale heterogeneous graph for dependencies
• Uses graph propagation for accurate missing value imputation