UniMove: A Unified Model for Multi-city Human Mobility Prediction

TL;DR

UniMove is a unified model that effectively predicts human mobility across multiple cities by capturing diverse patterns and constructing universal spatial representations, significantly improving accuracy over existing city-specific models.

Contribution

The paper introduces UniMove, a novel unified architecture for multi-city human mobility prediction, addressing heterogeneity and spatial representation challenges.

Findings

Improves mobility prediction accuracy by over 10.2%.

Enables joint training on multi-city data for mutual enhancement.

Demonstrates effectiveness across diverse city datasets.

Abstract

Human mobility prediction is vital for urban planning, transportation optimization, and personalized services. However, the inherent randomness, non-uniform time intervals, and complex patterns of human mobility, compounded by the heterogeneity introduced by varying city structures, infrastructure, and population densities, present significant challenges in modeling. Existing solutions often require training separate models for each city due to distinct spatial representations and geographic coverage. In this paper, we propose UniMove, a unified model for multi-city human mobility prediction, addressing two challenges: (1) constructing universal spatial representations for effective token sharing across cities, and (2) modeling heterogeneous mobility patterns from varying city characteristics. We propose a trajectory-location dual-tower architecture, with a location tower for universal spatial encoding and a trajectory tower for sequential mobility modeling. We also design MoE Transformer blocks to adaptively select experts to handle diverse movement patterns. Extensive experiments across multiple datasets from diverse cities demonstrate that UniMove truly embodies the essence of a unified model. By enabling joint training on multi-city data with mutual data enhancement, it significantly improves mobility prediction accuracy by over 10.2\%. UniMove represents a key advancement toward realizing a true foundational model with a unified architecture for human mobility. We release the implementation at https://github.com/tsinghua-fib-lab/UniMove/.