为不同人群定制专家模型，实现公平无损的医疗预测。
Achieving Fairness Without Harm via Selective Demographic Experts
- 按人群学习专属表征，动态选择最适合的专家模型。
- 在三种医学数据集上同时提升公平性与准确率。
- 适合高风险场景，如临床诊断，兼顾伦理与性能。
随着机器学习系统越来越多地应用于医疗等以人为中心的领域，确保公平性的同时保持高预测性能至关重要。现有偏见缓解方法往往在公平性与准确性之间造成权衡，无意中降低了某些人口群体的表现。在临床诊断等高风险领域，这种权衡在伦理和实践上均不可接受。本研究提出一种无损害公平性方法：为不同人口群体学习独立表征，并通过无损害约束选择特定于群体的专家模型（包含群体专属表征与个性化分类器）。我们在三个真实世界医学数据集——涵盖眼部疾病、皮肤癌和胸部X光诊断——以及两个面部数据集上评估该方法。大量实证结果表明，该方法能在不损害任何群体表现的前提下有效实现公平性。
原文摘要 · Abstract (English)
As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a trade-off between fairness and accuracy, inadvertently degrading performance for certain demographic groups. In high-stakes domains like clinical diagnosis, such trade-offs are ethically and practically unacceptable. In this study, we propose a fairness-without-harm approach by learning distinct representations for different demographic groups and selectively applying demographic experts consisting of group-specific representations and personalized classifiers through a no-harm constrained selection. We evaluate our approach on three real-world medical datasets -- covering eye disease, skin cancer, and X-ray diagnosis -- as well as two face datasets. Extensive empirical results demonstrate the effectiveness of our approach in achieving fairness without harm.
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。