对比三种去偏方法，发现分层采样和GraphSAGE生成数据最有效
Comparing Methods for Bias Mitigation in Graph Neural Networks
- 用分层采样与GraphSAGE生成数据来降低图神经网络偏差
- 在德国信贷数据集上，公平性指标均提升，性能未下降
- 适合关注模型公平性且需保持性能的研究者参考
本文研究图神经网络（GNNs）在生成式人工智能（GenAI）系统数据准备中的关键作用，重点探讨并缓解偏差问题。对比了三种去偏方法：数据稀疏化、特征修改和合成数据增强。基于德国信贷数据集的实验表明，所有方法相比原始数据均提升了公平性指标（包括统计均等、机会平等和假阳性率）。其中，分层采样与使用GraphSAGE生成的合成数据在平衡人口统计分布的同时，有效维持了模型性能，为构建更公平且高效的AI系统提供了实践指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。