Urban region embeddings improve by combining mobility patterns and connections
Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding
Machine LearningArtificial Intelligence
Summary
Predicting things like crime or income in city areas depends on understanding how people move around and how regions connect over time. The authors found that previous methods didn’t fully use how these movement patterns change throughout the day or how connections between places appear and disappear. They developed a new approach called MoSS that looks at the hourly flow of people in and out of areas and at how these connections evolve over time. By combining these views in a special way, their method better captures important signals, helping improve predictions for cities like New York and Chicago.
urban region embeddinghuman mobilitytemporal dynamicszigzag persistence diagramssequence viewstructure viewmulti-degree interactionscross-view synergyurban sensingrepresentation learning
Authors
Namwoo Kim, Jeeyun Chang, Kanghoon Lee, Yoonjin Yoon
Abstract
Urban region embeddings have shown promising results in diverse urban sensing tasks such as crime, income, and service-call prediction. Recent methods improve representation quality by integrating mobility data with auxiliary modalities, using cross-view attention or contrastive objectives to align heterogeneous features into a unified region representation. However, leveraging the temporal dynamics of human mobility remains under-explored. Regional inflow and outflow fluctuate throughout the day, and inter-region connections emerge, persist, and dissolve over time. Moreover, prevailing fusion strategies combine views additively and miss the joint signal that emerges only when views co-occur. To address these gaps, we propose Mobility Stream-Structure Synergy (MoSS), which derives complementary views from mobility data: a Sequence view that preserves each region's hourly inflow/outflow profile, and a Structure view based on zigzag persistence diagrams that capture how regional connectivity emerges, persists, and dissolves over time. A synergy module then extracts emergent representations from the co-occurrence of these views through multi-degree interactions, explicitly capturing higher-order signal across views. Extensive experiments on New York City and Chicago show that MoSS achieves state-of-the-art performance across three downstream tasks using mobility data alone, outperforming baselines that rely on auxiliary modalities.