Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multimodal Contrastive Learning of Urban Space Representations from POI Data

About

Existing methods for learning urban space representations from Point-of-Interest (POI) data face several limitations, including issues with geographical delineation, inadequate spatial information modelling, underutilisation of POI semantic attributes, and computational inefficiencies. To address these issues, we propose CaLLiPer (Contrastive Language-Location Pre-training), a novel representation learning model that directly embeds continuous urban spaces into vector representations that can capture the spatial and semantic distribution of urban environment. This model leverages a multimodal contrastive learning objective, aligning location embeddings with textual POI descriptions, thereby bypassing the need for complex training corpus construction and negative sampling. We validate CaLLiPer's effectiveness by applying it to learning urban space representations in London, UK, where it demonstrates 5-15% improvement in predictive performance for land use classification and socioeconomic mapping tasks compared to state-of-the-art methods. Visualisations of the learned representations further illustrate our model's advantages in capturing spatial variations in urban semantics with high accuracy and fine resolution. Additionally, CaLLiPer achieves reduced training time, showcasing its efficiency and scalability. This work provides a promising pathway for scalable, semantically rich urban space representation learning that can support the development of geospatial foundation models. The implementation code is available at https://github.com/xlwang233/CaLLiPer.

Xinglei Wang, Tao Cheng, Stephen Law, Zichao Zeng, Lu Yin, Junyuan Liu• 2024

Related benchmarks

TaskDatasetResultRank
GDP predictionSingapore
R2 Score76.2
10
Land-Use Distribution mappingSingapore
KL Divergence54.9
10
Socioeconomic Distribution MappingLondon
KL Divergence34.1
10
Land Use ClassificationLondon
F1 Score35.5
10
Text-based Spatial POI RetrievalPOI dataset
Art Score34.65
9
Showing 5 of 5 rows

Other info

Follow for update