Urban Region Pre-training and Prompting: A Graph-based Approach

TL;DR

This paper introduces GURPP, a graph-based framework for pre-training and prompting urban region representations, capturing transferable knowledge and improving adaptability across diverse urban prediction tasks.

Contribution

The paper proposes a novel graph-based pre-training and prompting framework for urban regions, emphasizing fine-grained semantics and task adaptability.

Findings

Outperforms existing methods on multiple urban prediction tasks

Effectively captures heterogeneous and transferable patterns in urban regions

Enhances task adaptability through graph-based prompting methods

Abstract

Urban region representation is crucial for various urban downstream tasks. However, despite the proliferation of methods and their success, acquiring general urban region knowledge and adapting to different tasks remains challenging. Existing work pays limited attention to the fine-grained functional layout semantics in urban regions, limiting their ability to capture transferable knowledge across regions. Further, inadequate handling of the unique features and relationships required for different downstream tasks may also hinder effective task adaptation. In this paper, we propose a $\textbf{G}$raph-based $\textbf{U}$rban $\textbf{R}$egion $\textbf{P}$re-training and $\textbf{P}$rompting framework ($\textbf{GURPP}$) for region representation learning. Specifically, we first construct an urban region graph and develop a subgraph-centric urban region pre-training model to capture the heterogeneous and transferable patterns of entity interactions. This model pre-trains knowledge-rich region embeddings using contrastive learning and multi-view learning methods. To further refine these representations, we design two graph-based prompting methods: a manually-defined prompt to incorporate explicit task knowledge and a task-learnable prompt to discover hidden knowledge, which enhances the adaptability of these embeddings to different tasks. Extensive experiments on various urban region prediction tasks and different cities demonstrate the superior performance of our framework.