Bridging the Fairness Divide: Achieving Group and Individual Fairness in Graph Neural Networks

arXiv:2404.17511v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have emerged as a powerful tool for analyzing and learning from complex data structured as graphs, demonstrating remarkable effectiveness in various applications, such as social network analysis, recommendation systems, and drug discovery. However, despite their impressive performance, the fairness problem has increasingly gained attention as a crucial aspect to consider. Existing research in graph learning focuses on either group fairness or individual fairness. However, since each concept provides unique insights into …

abstract analysis applications arxiv cs.cy cs.lg cs.si data discovery drug discovery fairness gnns graph graph neural networks graphs however network networks neural networks performance recommendation recommendation systems social systems tool type