One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion

TL;DR

This paper introduces GenMove, a unified diffusion-based framework for various trajectory modeling tasks that leverages masked conditions and contextual embeddings to outperform specialized models.

Contribution

The work presents a novel general framework for trajectory modeling that unifies diverse tasks using masked conditions and contextual embeddings within a diffusion model.

Findings

Outperforms state-of-the-art baselines by up to 13% in generation tasks

Successfully handles diverse trajectory tasks with a single model

Demonstrates significant improvements across multiple mainstream tasks

Abstract

Trajectory data play a crucial role in many applications, ranging from network optimization to urban planning. Existing studies on trajectory data are task-specific, and their applicability is limited to the specific tasks on which they have been trained, such as generation, recovery, or prediction. However, the potential of a unified model has not yet been fully explored in trajectory modeling. Although various trajectory tasks differ in inputs, outputs, objectives, and conditions, they share common mobility patterns. Based on these common patterns, we can construct a general framework that enables a single model to address different tasks. However, building a trajectory task-general framework faces two critical challenges: 1) the diversity in the formats of different tasks and 2) the complexity of the conditions imposed on different tasks. In this work, we propose a general trajectory modeling framework via masked conditional diffusion (named GenMove). Specifically, we utilize mask conditions to unify diverse formats. To adapt to complex conditions associated with different tasks, we utilize historical trajectory data to obtain contextual trajectory embeddings, which include rich contexts such as spatiotemporal characteristics and user preferences. Integrating the contextual trajectory embedding into diffusion models through a classifier-free guidance approach allows the model to flexibly adjust its outputs based on different conditions. Extensive experiments on mainstream tasks demonstrate that our model significantly outperforms state-of-the-art baselines, with the highest performance improvement exceeding 13% in generation tasks.