# Multi-Graph Fusion Networks for Urban Region Embedding

arXiv: https://arxiv.org/abs/2201.09760 · HTML: https://mlsanity.com/paper/2201.09760/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [A Survey on Network Embedding](https://mlsanity.com/paper/1711.08752/) (2017)
- [Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning](https://mlsanity.com/paper/2201.02435/) (2022)

## Built on by (most cited first, 30 of 32)

- [INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging](https://mlsanity.com/paper/2302.02738/) (2023)
- [Automated Spatio-Temporal Graph Contrastive Learning](https://mlsanity.com/paper/2305.03920/) (2023)
- [Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction](https://mlsanity.com/paper/2302.13094/) (2023)
- [MuseCL: Predicting Urban Socioeconomic Indicators via Multi-Semantic Contrastive Learning](https://mlsanity.com/paper/2407.09523/) (2024)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation](https://mlsanity.com/paper/2306.10683/) (2023)
- [Urban Region Embedding via Multi-View Contrastive Prediction](https://mlsanity.com/paper/2312.09681/) (2023)
- [Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications](https://mlsanity.com/paper/2408.14806/) (2024)
- [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)
- [Self-Supervised Representation Learning for Geospatial Objects: A Survey](https://mlsanity.com/paper/2408.12133/) (2024)
- [Urban Region Pre-training and Prompting: A Graph-based Approach](https://mlsanity.com/paper/2408.05920/) (2024)
- [Spatial Heterophily Aware Graph Neural Networks](https://mlsanity.com/paper/2306.12139/) (2023)
- [Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction](https://mlsanity.com/paper/2411.00028/) (2024)
- [Demo2Vec: Learning Region Embedding with Demographic Information](https://mlsanity.com/paper/2409.16837/) (2024)
- [Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics](https://mlsanity.com/paper/2403.11495/) (2024)
- [MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale](https://mlsanity.com/paper/2506.01297/) (2025)
- [Boundary Prompting: Elastic Urban Region Representation via Graph-based Spatial Tokenization](https://mlsanity.com/paper/2503.07991/) (2025)
- [Urban In-Context Learning: Bridging Pretraining and Inference through Masked Diffusion for Urban Profiling](https://mlsanity.com/paper/2508.03042/) (2025)
- [Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision](https://mlsanity.com/paper/2511.07062/) (2025)
- [Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning](https://mlsanity.com/paper/2402.06135/) (2024)
- [Explainable Hierarchical Urban Representation Learning for Commuting Flow Prediction](https://mlsanity.com/paper/2408.14762/) (2024)
- [CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting](https://mlsanity.com/paper/2606.05413/) (2026)
- [Attentive Graph Enhanced Region Representation Learning](https://mlsanity.com/paper/2307.03212/) (2023)
- [A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning](https://mlsanity.com/paper/2509.23772/) (2025)
- [JiuTian Chuanliu: A Large Spatiotemporal Model for General-purpose Dynamic Urban Sensing](https://mlsanity.com/paper/2510.23662/) (2025)
- [Learning A Universal Crime Predictor with Knowledge-guided Hypernetworks](https://mlsanity.com/paper/2511.02336/) (2025)
- [Tracing Footsteps of Similar Cities: Modeling Urban Economic Vitality with Dynamic Inter-City Graph Embeddings](https://mlsanity.com/paper/2511.22325/) (2025)
- [ToPT: Task-Oriented Prompt Tuning for Urban Region Representation Learning](https://mlsanity.com/paper/2602.01610/) (2026)
- [MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction](https://mlsanity.com/paper/2608.18546/) (2026)

## Abstract (arXiv)

Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks. In this paper, we propose multi-graph fusion networks (MGFN) to enable the cross domain prediction tasks. First, we integrate the graphs with spatio-temporal similarity as mobility patterns through a mobility graph fusion module. Then, in the mobility pattern joint learning module, we design the multi-level cross-attention mechanism to learn the comprehensive embeddings from multiple mobility patterns based on intra-pattern and inter-pattern messages. Finally, we conduct extensive experiments on real-world urban datasets. Experimental results demonstrate that the proposed MGFN outperforms the state-of-the-art methods by up to 12.35% improvement.