Comparing Methods for Bias Mitigation in Graph Neural Networks

Barbara Hoffmann, Ruben Mayer

Student Lead Author Indication: Yes

Keywords: Bias, Graph Neural Networks, Data Preparation Tool

TL;DR: Comparative evaluation of three distinct bias mitigation methods for GNNs, assessed using multiple fairness metrics.

Abstract: This paper examines the critical role of Graph Neural Networks (GNNs) in data preparation for generative artificial intelligence (GenAI) systems, with a particular focus on addressing and mitigating biases. We present a comparative analysis of three distinct methods for bias mitigation: data sparsification, feature modification, and synthetic data augmentation. Through experimental analysis using the german credit dataset, we evaluate these approaches using multiple fairness metrics, including statistical parity, equality of opportunity, and false positive rates. Our research demonstrates that while all methods improve fairness metrics compared to the original dataset, stratified sampling and synthetic data augmentation using GraphSAGE prove particularly effective in balancing demographic representation while maintaining model performance. The results provide practical insights for developing more equitable AI systems while maintaining model performance.

Submission Number: 30