2023/06/16 by T. Liu, Liu, Tingwei, Peizhao Li +3 · 1 citation
Environmental Science · Social Sciences · #FOS: Computer and information sciences #Health disparities and outcomes #Health, Environment, Cognitive Aging #Machine Learning (cs.LG) #Privacy, Security, and Data Protection #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2306.10123
openalex publication_date 2023/06/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Fair graph partition of social networks is a crucial step toward ensuring fair and non-discriminatory treatments in unsupervised user analysis. Current fair partition methods typically consider node balance, a notion pursuing a proportionally balanced number of nodes from all demographic groups, but ignore the bias induced by imbalanced edges in each cluster. To address this gap, we propose a notion edge balance to measure the proportion of edges connecting different demographic groups in clusters. We analyze the relations between node balance and edge balance, then with line graph transformations, we propose a co-embedding framework to learn dual node and edge fairness-aware representations for graph partition. We validate our framework through several social network datasets and observe balanced partition in terms of both nodes and edges along with good utility. Moreover, we demonstrate our fair partition can be used as pseudo labels to facilitate graph neural networks to behave fairly in node classification and link prediction tasks.