Learning urban region representations with POIs and hierarchical graph infomax

• Main Authors: Huang, Weiming, Zhang, Daokun, Mai, Gengchen, Guo, Xu, Cui, Lizhen
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Urban Region Embedding; Hierarchical Graph Infomax
• Online Access: https://hdl.handle.net/10356/169131
• Institution: Nanyang Technological University

We present the hierarchical graph infomax (HGI) approach for learning urban region representations (vector embeddings) with points-of-interest (POIs) in a fully unsupervised manner, which can be used in various downstream tasks. Specifically, HGI comprises several key steps: (1) training category em...