HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Qianru, Gao, Xinyi, Wang, Haixin, Huang, Dong, Yiu, Siu-Ming, Yin, Hongzhi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913989619875840
author Zhang, Qianru
Gao, Xinyi
Wang, Haixin
Huang, Dong
Yiu, Siu-Ming
Yin, Hongzhi
author_facet Zhang, Qianru
Gao, Xinyi
Wang, Haixin
Huang, Dong
Yiu, Siu-Ming
Yin, Hongzhi
contents Spatial-temporal graph representations play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, a key challenge lies in the noisy and sparse nature of spatial-temporal data, which limits existing neural networks' ability to learn meaningful region representations in the spatial-temporal graph. To overcome these limitations, we propose HGAurban, a novel heterogeneous spatial-temporal graph masked autoencoder that leverages generative self-supervised learning for robust urban data representation. Our framework introduces a spatial-temporal heterogeneous graph encoder that extracts region-wise dependencies from multi-source data, enabling comprehensive modeling of diverse spatial relationships. Within our self-supervised learning paradigm, we implement a masked autoencoder that jointly processes node features and graph structure. This approach automatically learns heterogeneous spatial-temporal patterns across regions, significantly improving the representation of dynamic temporal correlations. Comprehensive experiments across multiple spatiotemporal mining tasks demonstrate that our framework outperforms state-of-the-art methods and robustly handles real-world urban data challenges, including noise and sparsity in both spatial and temporal dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning
Zhang, Qianru
Gao, Xinyi
Wang, Haixin
Huang, Dong
Yiu, Siu-Ming
Yin, Hongzhi
Machine Learning
Spatial-temporal graph representations play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, a key challenge lies in the noisy and sparse nature of spatial-temporal data, which limits existing neural networks' ability to learn meaningful region representations in the spatial-temporal graph. To overcome these limitations, we propose HGAurban, a novel heterogeneous spatial-temporal graph masked autoencoder that leverages generative self-supervised learning for robust urban data representation. Our framework introduces a spatial-temporal heterogeneous graph encoder that extracts region-wise dependencies from multi-source data, enabling comprehensive modeling of diverse spatial relationships. Within our self-supervised learning paradigm, we implement a masked autoencoder that jointly processes node features and graph structure. This approach automatically learns heterogeneous spatial-temporal patterns across regions, significantly improving the representation of dynamic temporal correlations. Comprehensive experiments across multiple spatiotemporal mining tasks demonstrate that our framework outperforms state-of-the-art methods and robustly handles real-world urban data challenges, including noise and sparsity in both spatial and temporal dimensions.
title HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning
topic Machine Learning
url https://arxiv.org/abs/2410.10915