Learning Demographic-Conditioned Mobility Trajectories with Aggregate Supervision

2026-03-03

AI Summary

This work addresses the challenge that existing trajectory generation models struggle to capture heterogeneous mobility patterns across demographic groups, primarily due to the absence of individual-level demographic labels in trajectory data. To overcome this limitation, the authors propose ATLAS, a novel method that, for the first time, enables demographically conditioned generation of high-fidelity individual trajectories using only weakly supervised signals—namely, aggregated regional mobility statistics and census-derived population composition. ATLAS enforces consistency between generated trajectories and observed aggregate patterns at the regional level and is grounded in theoretical analysis that characterizes its conditions for effectiveness. Experiments on real-world datasets demonstrate that ATLAS substantially improves demographic realism (reducing Jensen-Shannon divergence by 12%–69%) and achieves performance comparable to strong supervised baselines, thereby validating the practical relevance of the theoretical insights.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Human mobility trajectories are widely studied in public health and social science, where different demographic groups exhibit significantly different mobility patterns. However, existing trajectory generation models rarely capture this heterogeneity because most trajectory datasets lack demographic labels. To address this gap in data, we propose ATLAS, a weakly supervised approach for demographic-conditioned trajectory generation using only (i) individual trajectories without demographic labels, (ii) region-level aggregated mobility features, and (iii) region-level demographic compositions from census data. ATLAS trains a trajectory generator and fine-tunes it so that simulated mobility matches observed regional aggregates while conditioning on demographics. Experiments on real trajectory data with demographic labels show that ATLAS substantially improves demographic realism over baselines (JSD $\downarrow$ 12%--69%) and closes much of the gap to strongly supervised training. We further develop theoretical analyses for when and why ATLAS works, identifying key factors including demographic diversity across regions and the informativeness of the aggregate feature, paired with experiments demonstrating the practical implications of our theory. We release our code at https://github.com/schang-lab/ATLAS.

Problem

• human mobility
• demographic heterogeneity
• trajectory generation
• aggregate supervision
• data labeling gap

Innovation

• weakly supervised learning
• demographic-conditioned trajectory generation
• aggregate supervision
• human mobility modeling
• spatial-temporal generative model