FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization

arXiv:2403.12474v1 Announce Type: new
Abstract: Despite the remarkable success of graph neural networks (GNNs) in modeling graph-structured data, like other machine learning models, GNNs are also susceptible to making biased predictions based on sensitive attributes, such as race and gender. For fairness consideration, recent state-of-the-art (SOTA) methods propose to filter out sensitive information from inputs or representations, e.g., edge dropping or feature masking. However, we argue that such filtering-based strategies may also filter out some non-sensitive feature information, leading to …

abstract art arxiv cs.cy cs.lg data fairness gender gnns graph graph neural networks information machine machine learning machine learning models making modeling networks neural networks predictions race race and gender sota state structured data success through type