标题
: Urban region representation learning <i>via</i> dual spatial contrasts作者: Qin, Q (Qin, Quan); Ai, TH (Ai, Tinghua); Huang, WM (Huang, Weiming); Xu, SS (Xu, Shishuo); Du, MY (Du, Mingyi); Li, SN (Li, Songnian)
来源出版物: INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE DOI: 10.1080/13658816.2025.2585320 Early Access Date: NOV 2025 Published Date: 2025 NOV 13
摘要: Region representation learning emerges as a new research paradigm to encode urban systems and facilitate geographic mapping. Recent studies have sought to reasonably introduce inductive biases, which refer to prior assumptions that guide model learning, from a geospatial perspective to improve the quality of region representations. However, there remain challenges in incorporating the spatial effects, e.g. spatial dependency and spatial heterogeneity, into inductive biases, as they are critical to the geographic awareness of region representations. In response, we developed a novel region representation learning framework, termed Region Graph Spatial Contrastive Learning (RGSCL), by leveraging building footprints and points of interest (POIs) along with prior spatial knowledge to derive region representations. Specifically, RGSCL first constructed multi-view region graphs with POIs, building footprints and their spatial proximity, to form a base representation space. Next, the algorithm adopted a contrastive learning mechanism with spatial effects to formulate a dual-spatial-contrast loss function to optimise the representation space. The dual-spatial-contrasts captured POI-building spatial dependency and the region's spatial heterogeneity to compose semantics in region representations. Experimental results demonstrated that RGSCL improved performance in geographic mapping. This study offers new insights into GeoAI from the perspective of inductive biases with respect to spatial effects.
作者关键词: Spatial representation learning; spatial effect; contrastive learning; building footprints; points of interest
地址: [Qin, Quan; Ai, Tinghua] Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Peoples R China.
[Huang, Weiming] Univ Leeds, Sch Geog, Leeds, England.
[Xu, Shishuo; Du, Mingyi] Beijing Univ Civil Engn & Architecture, Sch Geomat & Urban Spatial Informat, Beijing, Peoples R China.
[Li, Songnian] Toronto Metropolitan Univ, Dept Civil Engn, Toronto, ON, Canada.
通讯作者地址: Ai, TH (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Peoples R China.
电子邮件地址: [email protected]
影响因子：5.
