GCN-TULHOR: Trajectory-User Linking Leveraging GCNs and Higher-Order Spatial Representations

2025-09-14

AI Summary

Trajectory–user linking (TUL) aims to accurately associate anonymous mobility trajectories with their originating users, which is critical for personalized recommendation and location-based service security. Existing approaches struggle to model complex spatial dependencies in sparse and incomplete trajectories, and often over-rely on low-level check-ins or auxiliary features (e.g., timestamps, POIs). This paper proposes a hexagonal-grid-based high-order mobility representation framework that maps raw trajectories onto structured flow graphs and employs graph convolutional networks (GCNs) to capture non-local spatial patterns. Crucially, it unifies sparse check-in and continuous GPS data without requiring external features. Evaluated on six real-world datasets, our method consistently outperforms traditional models and RNN/Transformer baselines, achieving up to 8% absolute gains in accuracy and F1-score. The optimal configuration—single-layer GCN with 512-dimensional embeddings—demonstrates strong robustness, generalizability, and scalability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Planning with Language Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Trajectory-user linking (TUL) aims to associate anonymized trajectories with the users who generated them, which is crucial for personalized recommendations, privacy-preserving analytics, and secure location-based services. Existing methods struggle with sparse data, incomplete routes, and limited modeling of complex spatial dependencies, often relying on low-level check-in data or ignoring spatial patterns. In this paper, we introduced GCN-TULHOR, a method that transforms raw location data into higher-order mobility flow representations using hexagonal tessellation, reducing data sparsity and capturing richer spatial semantics, and integrating Graph Convolutional Networks (GCNs). Our approach converts both sparse check-in and continuous GPS trajectory data into unified higher-order flow representations, mitigating sparsity while capturing deeper semantic information. The GCN layer explicitly models complex spatial relationships and non-local dependencies without requiring side information such as timestamps or points of interest. Experiments on six real-world datasets show consistent improvements over classical baselines, RNN- and Transformer-based models, and the TULHOR method in accuracy, precision, recall, and F1-score. GCN-TULHOR achieves 1-8% relative gains in accuracy and F1. Sensitivity analysis identifies an optimal setup with a single GCN layer and 512-dimensional embeddings. The integration of GCNs enhances spatial learning and improves generalizability across mobility data. This work highlights the value of combining graph-based spatial learning with sequential modeling, offering a robust and scalable solution for TUL with applications in recommendations, urban planning, and security.

Problem

• Linking anonymized trajectories to users for personalized services
• Overcoming sparse data and incomplete routes in mobility analysis
• Modeling complex spatial dependencies without additional metadata

Innovation

• Uses hexagonal tessellation for higher-order flow representations
• Integrates Graph Convolutional Networks for spatial dependencies
• Converts sparse data into unified spatial semantic embeddings