Graph Supervised Contrastive Learning for Geodemographics
Keywords: Graph Neural Network, Geodemographics
Abstract: Geodemographic analysis is essential for understanding population characteristics and addressing socio-economic disparities across regions. However, limited research has been conducted on modelling changes in demographic data over time using Graph Neural Networks (GNNs). In this study, we address this gap by leveraging GNNs to model correlations between the 2011 census data (England \& Wales), observing changes over time, and the Output Area Classification 2021, which reflects socio-economic differences between Output Areas. We propose a novel framework that utilises Supervised Contrastive Learning on graphs to obtain robust OA embeddings, with a particular focus on improving the model’s performance for minority classes. To evaluate the effectiveness of our framework, we conducted two downstream tasks based on the 2021 OA embeddings. Our results demonstrate that the proposed approach provides valuable insights for geodemographic analysis and offers policymakers a useful tool for assessing socio-economic transitions over time, and planning ahead on the basis of it.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6797
Loading