Learning Demographic-Conditioned Mobility Trajectories with Aggregate Supervision
2026-03-03 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a method called ATLAS to generate movement patterns (trajectories) of people that reflect differences between demographic groups, even when individual data lacks labels like age or gender. They use weak supervision by combining unlabeled movement data, regional mobility statistics, and census demographic info to train the model. Their experiments show ATLAS produces more realistic demographic movement patterns compared to previous methods. They also provide a theory to explain when and why their approach works well. Their code is available for others to use.
human mobility trajectoriesdemographic heterogeneityweakly supervised learningtrajectory generationmobility datacensus dataregional aggregatesmodel fine-tuningstatistical divergencepublic health
Authors
Jessie Z. Li, Zhiqing Hong, Toru Shirakawa, Serina Chang
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.