Urban region embeddings improve by combining mobility flow and connectivity patterns
Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding
Machine LearningArtificial Intelligence
Summary
Understanding how people move around a city can help predict things like crime rates or income levels in different neighborhoods. The authors found that current methods often miss the time patterns of these movements and how areas connect differently throughout the day. They created a new way to capture both the flow of people in and out of areas and the changing connections between regions over time. Their approach combines these two views in a way that finds new insights and performs better than older methods, even without extra data types.
What this means in practice
- •For urban planners: Predict socioeconomic indicators and public safety risks using only human mobility data to help plan city services.
- •For transportation analysts: Model and monitor evolving regional connections and traffic flows throughout the day to improve transit planning.
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.