TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

2026-03-19

AI Summary

Real-world urban trajectory data are often sparse and discontinuous due to low sampling rates and insufficient spatial coverage, hindering their utility for high-precision location-based services. To address this challenge, this work proposes TRACE, a diffusion-based generative model that introduces a State Propagation Diffusion Model (SPDM). By incorporating a memory mechanism during the denoising process, SPDM effectively leverages historical intermediate states to faithfully reconstruct missing trajectory segments under complex spatiotemporal patterns. The model supports end-to-end training and achieves state-of-the-art performance across multiple real-world datasets, improving trajectory reconstruction accuracy by over 26% compared to existing methods while maintaining computationally feasible inference costs.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for trajectory recovery named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering $>$26\% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at: https://github.com/JinmingWang/TRACE

Problem

• trajectory recovery
• sparse trajectories
• urban mobility
• GPS data
• spatio-temporal patterns

Innovation

• trajectory recovery
• diffusion model
• state propagation
• memory mechanism
• urban mobility