EqGNN: Equalized Node Opportunity in Graphs

• Published in: arXiv.org
• Main Authors: Singer, Uriel, Radinsky, Kira
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 19.08.2021
• Subjects: Algorithms; Classifiers; Cognitive tasks; Criteria; Graph neural networks; Graphs; Optimization; Permutations; Statistical methods; Supervised learning

Graph neural networks (GNNs), has been widely used for supervised learning tasks in graphs reaching state-of-the-art results. However, little work was dedicated to creating unbiased GNNs, i.e., where the classification is uncorrelated with sensitive attributes, such as race or gender. Some ignore th...