Fine-Grained Urban Flow Inference with Multi-scale Representation Learning

TL;DR

This paper introduces UrbanMSR, a novel multi-scale representation learning model using self-supervised contrastive learning to improve fine-grained urban flow inference by capturing dynamic interactions across multiple geographic scales.

Contribution

The paper proposes a new multi-scale representation learning approach with self-supervised contrastive learning for dynamic urban flow inference, addressing limitations of static single-scale methods.

Findings

UrbanMSR outperforms state-of-the-art methods on three real-world datasets.

Multi-scale fusion improves fine-grained inference accuracy.

Dynamic representations capture temporal and spatial interactions effectively.

Abstract

Fine-grained urban flow inference (FUFI) is a crucial transportation service aimed at improving traffic efficiency and safety. FUFI can infer fine-grained urban traffic flows based solely on observed coarse-grained data. However, most of existing methods focus on the influence of single-scale static geographic information on FUFI, neglecting the interactions and dynamic information between different-scale regions within the city. Different-scale geographical features can capture redundant information from the same spatial areas. In order to effectively learn multi-scale information across time and space, we propose an effective fine-grained urban flow inference model called UrbanMSR, which uses self-supervised contrastive learning to obtain dynamic multi-scale representations of neighborhood-level and city-level geographic information, and fuses multi-scale representations to improve fine-grained accuracy. The fusion of multi-scale representations enhances fine-grained. We validate the performance through extensive experiments on three real-world datasets. The resutls compared with state-of-the-art methods demonstrate the superiority of the proposed model.