Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic

TL;DR

This paper introduces MobTA, a novel zero-shot trajectory generation method that leverages task arithmetic and bus timetables to generate mobility trajectories for a target city without any real data from it.

Contribution

It presents the first approach to apply task arithmetic to mobility trajectory generation, enabling zero-shot predictions using only source data and bus timetables.

Findings

MobTA outperforms existing methods in zero-shot scenarios.

MobTA achieves results close to models trained on target city data.

Theoretical analysis confirms MobTA's stability across different LLMs.

Abstract

Mobility trajectory data provide essential support for smart city applications. However, such data are often difficult to obtain. Meanwhile, most existing trajectory generation methods implicitly assume that at least a subset of real mobility data from target city is available, which limits their applicability in data-inaccessible scenarios. In this work, we propose a new problem setting, called bus-conditioned zero-shot trajectory generation, where no mobility trajectories from a target city are accessible. The generation process relies solely on source city mobility data and publicly available bus timetables from both cities. Under this setting, we propose MobTA, the first approach to introduce task arithmetic into trajectory generation. MobTA models the parameter shift from bus-timetable-based trajectory generation to mobility trajectory generation in source city, and applies this shift to target city through arithmetic operations on task vectors. This enables trajectory generation that reflects target-city mobility patterns without requiring any real mobility data from it. Furthermore, we theoretically analyze MobTA's stability across base and instruction-tuned LLMs. Extensive experiments show that MobTA significantly outperforms existing methods, and achieves performance close to models finetuned using target city mobility trajectories.