提出可扩展的路径特定反事实公平性方法，解决高维数据下公平性评估难题。
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
- 将路径特定反事实公平性转化为因果条件独立约束，避免复杂估计
- 在高维医学图像等场景中仍保持可扩展性，不依赖密度估计
- 适合关注模型公平性的算法研究者与医疗AI开发者
深度学习模型在预测时可能无意间受敏感属性影响，引发公平性问题。现有路径特定反事实公平性方法依赖边际潜在结果概率估计，该方法需高维条件密度估计，在医学图像等高维模态中因维度灾难导致估计不可靠。为此，本文将路径特定反事实公平性问题转化为因果条件独立约束，并证明满足该约束即可消除不公平因果效应。这一转化将原本难以处理的反事实估计替换为可判别优化目标，使方法在高维场景下依然具备可扩展性。
原文摘要 · Abstract (English)
Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing attempts to make Path-Specific Counterfactual Fairness optimizable rely on estimating marginal potential outcome probabilities-an approach that fundamentally requires high-dimensional conditional density estimation and breaks down in modalities such as medical images, where the curse of dimensionality renders reliable estimation infeasible. To address this limitation, we reduce the problem of enforcing Path-Specific Counterfactual Fairness to a causal conditional independence constraint and prove that satisfying this constraint is sufficient to eliminate the unfair causal effect. This reduction replaces intractable counterfactual estimation with a discriminative optimization objective that remains scalable in high-dimensional settings.
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。