提出兼顾公平与隐私的分类算法，实现高精度公平性同时保护数据隐私。
Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
- 设计后处理算法DP2DP，同步满足群体公平与差分隐私。
- 理论证明其收敛速度接近最优非私有方法，仅慢对数因子。
- 在真实与合成数据上表现优异，是当前最佳平衡方案。
机器学习在敏感场景中的应用日益广泛，亟需同时保障数据隐私与跨敏感子群体的公平性。尽管隐私与公平各自研究深入，但二者协同仍不清晰。现有研究常将两者视为冲突目标，认为强隐私机制如差分隐私必然损害公平性。本文挑战这一观点，表明差分隐私可融入公平增强流程且对公平性影响极小。我们提出后处理算法DP2DP，同时实现群体公平（demographic parity）与差分隐私。理论分析显示，该算法收敛至群体公平目标的速度几乎与最优非私有方法相当（仅慢对数因子）。在合成与真实数据集上的实验验证了理论结果，表明所提算法在准确率、公平性与隐私间达到当前最优权衡。
原文摘要 · Abstract (English)
The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been extensively studied, their joint treatment remains poorly understood. Existing research often frames them as conflicting objectives, with multiple studies suggesting that strong privacy notions such as differential privacy inevitably compromise fairness. In this work, we challenge that perspective by showing that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees. We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy. Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate (up logarithmic factor) as the best non-private methods from the literature. Experiments on both synthetic and real datasets confirm our theoretical results, showing that the proposed algorithm achieves state-of-the-art accuracy/fairness/privacy trade-offs.
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。