Work

Analyzing world city network by graph convolutional networks

Year: 2024

Type: article

Abstract: British scholar Peter Taylor constructed the World City Network by analyzing the office networks of multinational companies, enabling a network perspective on world cities. However, this method has long been hindered by data deficiencies and update delays. In this study, we utilized publicly available, real-time updated data on global routes to construct the World City Network, thereby addressing the issues of data insufficiency and delayed updates in the existing model. For the first time, advanced Graph Convolutional Networks were employed to analyze the World City Network, and we introduced GCNRank. Finally, we compared GCNRank with other centrality measures and found that GCNRank provides a more detailed representation of city rankings and effectively avoids local optima.

Source: Scientific Reports

DOI: 10.1038/s41598-024-69494-1

Authors: Linfang Tian, Weixiong Rao, Kai Zhao, Huy T. Vo

Institutions: Tongji University, Georgia State University, City College of New York, City University of New York, New York University

Language: English

Topic: Global Urban Networks and Dynamics

Subfield: Urban Studies

Field: Social Sciences

Domain: Social Sciences

SDG: Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $2,590