用生成模型在推理时修正偏差，让已部署的机器学习系统更公平
BiasGuard: Guardrailing Fairness in Machine Learning Production Systems
- 通过条件生成对抗网络在推理时合成反向属性数据，实现公平性干预
- 在多个数据集上使公平性提升31%，准确率仅下降0.09%
- 无需重新训练模型，适合无法修改训练流程的生产环境
随着机器学习系统在招聘、金融风控和刑事司法等关键领域应用日益广泛，确保公平性的重要性愈发突出。尽管现有研究多聚焦于训练数据与过程的改进，对已部署系统输出的公平性关注仍显不足。本文提出‘BiasGuard’，一种面向生产环境的公平性防护机制。该方法利用基于条件生成对抗网络（CTGAN）的测试时增强（TTA），生成受保护属性值反转后的数据样本，从而促进不同群体间的公平结果。该策略可在不重新训练模型的前提下，为特权与非特权群体提供均等机会，显著提升部署系统公平性。在多个数据集上的全面实验表明，与未缓解偏差的基准相比，BiasGuard使公平性提升31%，准确率仅降低0.09%。此外，其性能优于现有后处理方法，为无法重训练的场景提供了有效的偏见防护工具。
原文摘要 · Abstract (English)
As machine learning (ML) systems increasingly impact critical sectors such as hiring, financial risk assessments, and criminal justice, the imperative to ensure fairness has intensified due to potential negative implications. While much ML fairness research has focused on enhancing training data and processes, addressing the outputs of already deployed systems has received less attention. This paper introduces 'BiasGuard', a novel approach designed to act as a fairness guardrail in production ML systems. BiasGuard leverages Test-Time Augmentation (TTA) powered by Conditional Generative Adversarial Network (CTGAN), a cutting-edge generative AI model, to synthesize data samples conditioned on inverted protected attribute values, thereby promoting equitable outcomes across diverse groups. This method aims to provide equal opportunities for both privileged and unprivileged groups while significantly enhancing the fairness metrics of deployed systems without the need for retraining. Our comprehensive experimental analysis across diverse datasets reveals that BiasGuard enhances fairness by 31% while only reducing accuracy by 0.09% compared to non-mitigated benchmarks. Additionally, BiasGuard outperforms existing post-processing methods in improving fairness, positioning it as an effective tool to safeguard against biases when retraining the model is impractical.
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。