analiza aiqbench
This research introduces MoSS, a novel framework that enhances urban region embeddings by synergistically fusing temporal mobility sequences with topological structures derived from persistence diagrams. By capturing higher-order interactions between these views without relying on auxiliary data, the method achieves state-of-the-art performance in predicting crime, income, and service calls across major cities like New York and Chicago. The work advances machine learning applications in urban sensing by demonstrating that intrinsic mobility dynamics alone can yield superior representations compared to traditional multi-modal approaches.
Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding
arXiv:2609.08268v1 Announce Type: new 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.08268 [cs.LG]
(or arXiv:2609.08268v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.08268 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 286 cuvinte
Subiecte conexe
Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction
arXiv · 29 iul. 2026
Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs
arXiv · 17 aug. 2026
Graph-centric agentic intelligence
Amazon Science · 1 oct. 2026
MMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments
arXiv · 22 sept. 2026