arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.02243cs.LG
收藏

公平回归中的覆盖机会均等

Equal Opportunity of Coverage in Fair Regression

University of Illinois Chicago(伊利诺伊大学芝加哥分校);ByteDance Research(字节跳动研究院)

Fangxin Wang, Lu Cheng, Ruocheng Guo, Kay Liu, Philip S. Yu

AI总结:

针对现有均等覆盖公平性方法在细粒度群体及不确定性评估上的不足,提出覆盖机会均等(EOC)概念及无分布后处理方法BFQR,可在维持预定覆盖率与合理区间宽度的同时提升EOC,实验验证了其有效性。

摘要:

我们研究预测不确定性下的公平机器学习(ML),以实现可靠且可信赖的决策。具有开创性的“均等覆盖”工作提出了一种感知不确定性的公平性概念。然而,它无法保证在以真实标签为条件的更细粒度群体(例如低收入女性)之间实现相等的覆盖率,并且在不确定性评估方面存在偏差。为解决这些局限,我们提出了一种新的感知不确定性公平性——覆盖机会均等(Equal Opportunity of Coverage, EOC),其旨在实现两个特性:(1)具有相似结果的不同群体的覆盖率相近;(2)整体人群的覆盖率保持在预定水平。此外,预测区间应较窄以具备信息性。我们提出了分箱公平分位数回归(Binned Fair Quantile Regression, BFQR),这是一种无分布后处理方法,可为任何已训练的ML模型提升EOC并维持合理的区间宽度。该方法首先在留出集上进行校准,以限制与EOC的偏差,然后利用共形预测在测试集上保持EOC,同时优化预测区间宽度。实验结果证明了我们的方法在提升EOC方面的有效性。我们的代码已公开于https://github.com/fangxin-wang/bfqr 。

英文摘要:

We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. The seminal work of ``equalized coverage'' proposed an uncertainty-aware fairness notion. However, it does not guarantee equal coverage rates across more fine-grained groups (e.g., low-income females) conditioning on the true label and is biased in the assessment of uncertainty. To tackle these limitations, we propose a new uncertainty-aware fairness -- Equal Opportunity of Coverage (EOC) -- that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level. Further, the prediction intervals should be narrow to be informative. We propose Binned Fair Quantile Regression (BFQR), a distribution-free post-processing method to improve EOC with reasonable width for any trained ML models. It first calibrates a hold-out set to bound deviation from EOC, then leverages conformal prediction to maintain EOC on a test set, meanwhile optimizing prediction interval width. Experimental results demonstrate the effectiveness of our method in improving EOC. Our code is publicly available at https://github.com/fangxin-wang/bfqr .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑