UrbanVerse: Learning Urban Region Representation Across Cities and Tasks

TL;DR

UrbanVerse is a novel foundation model for urban analytics that generalizes across cities and tasks by focusing on local and structural features, using graph-based region modeling and a cross-task learning module, significantly improving prediction accuracy.

Contribution

The paper introduces UrbanVerse, a cross-city and cross-task urban representation learning framework with a novel graph-based region modeling and a versatile cross-task module, enhancing urban analytics performance.

Findings

Outperforms state-of-the-art methods across six urban prediction tasks.

Achieves up to 35.89% improvement in accuracy in cross-city settings.

Demonstrates strong generalization capabilities across diverse urban datasets.

Abstract

Recent advances in urban region representation learning have enabled a wide range of applications in urban analytics, yet existing methods remain limited in their capabilities to generalize across cities and analytic tasks. We aim to generalize urban representation learning beyond city- and task-specific settings, towards a foundation-style model for urban analytics. To this end, we propose UrbanVerse, a model for cross-city urban representation learning and cross-task urban analytics. For cross-city generalization, UrbanVerse focuses on features local to the target regions and structural features of the nearby regions rather than the entire city. We model regions as nodes on a graph, which enables a random walk-based procedure to form "sequences of regions" that reflect both local and neighborhood structural features for urban region representation learning. For cross-task generalization, we propose a cross-task learning module named HCondDiffCT. This module integrates region-conditioned prior knowledge and task-conditioned semantics into the diffusion process to jointly model multiple downstream urban prediction tasks. HCondDiffCT is generic. It can also be integrated with existing urban representation learning models to enhance their downstream task effectiveness. Experiments on real-world datasets show that UrbanVerse consistently outperforms state-of-the-art methods across six tasks under cross-city settings, achieving up to 35.89% improvements in prediction accuracy.