M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling

TL;DR

M-STAR introduces a multi-scale autoregressive framework for long-term human mobility trajectory generation, effectively capturing hierarchical spatiotemporal patterns and outperforming existing methods in fidelity and efficiency.

Contribution

The paper presents M-STAR, a novel multi-scale spatiotemporal autoregressive model that improves long-term trajectory generation by combining hierarchical encoding with Transformer-based prediction.

Findings

Outperforms existing methods in trajectory fidelity.

Significantly improves generation speed.

Effectively models hierarchical mobility patterns.

Abstract

Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR.