# Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

arXiv: https://arxiv.org/abs/2609.08268 · HTML: https://mlsanity.com/paper/2609.08268/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering](https://mlsanity.com/paper/1708.01471/) (2017)
- [Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting](https://mlsanity.com/paper/2105.04100/) (2021)
- [Multi-Graph Fusion Networks for Urban Region Embedding](https://mlsanity.com/paper/2201.09760/) (2022)
- [Region Embedding with Intra and Inter-View Contrastive Learning](https://mlsanity.com/paper/2211.08975/) (2022)
- [Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction](https://mlsanity.com/paper/2302.13094/) (2023)
- [Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models](https://mlsanity.com/paper/2402.01749/) (2024)
- [Urban Region Embedding via Multi-View Contrastive Prediction](https://mlsanity.com/paper/2312.09681/) (2023)
- [FlexiReg: Flexible Urban Region Representation Learning](https://mlsanity.com/paper/2503.09128/) (2025)
- [Urban Region Representation Learning with Attentive Fusion](https://mlsanity.com/paper/2312.04606/) (2023)
- [Temporal Network Analysis Using Zigzag Persistence](https://mlsanity.com/paper/2205.11338/) (2022)
- [Visual Detection of Structural Changes in Time-Varying Graphs Using Persistent Homology](https://mlsanity.com/paper/1707.06683/) (2017)
- [Urban Region Pre-training and Prompting: A Graph-based Approach](https://mlsanity.com/paper/2408.05920/) (2024)
- [Using Zigzag Persistent Homology to Detect Hopf Bifurcations in Dynamical Systems](https://mlsanity.com/paper/2009.08972/) (2020)
- [Effective Urban Region Representation Learning Using Heterogeneous Urban Graph Attention Network (HUGAT)](https://mlsanity.com/paper/2202.09021/) (2022)
- [TopoCL: Topological Contrastive Learning for Time Series](https://mlsanity.com/paper/2502.02924/) (2025)
- [HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning](https://mlsanity.com/paper/2410.10915/) (2024)

## Abstract (arXiv)

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.