arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.09932cs.LGcs.AImath.OC
收藏

学习最优公平分类树:可解释性、公平性与准确性之间的权衡

Learning Optimal Fair Classification Trees: Trade-offs Between Interpretability, Fairness, and Accuracy

USC Center for AI in Society(南加州大学人工智能与社会中心);University of Southern California(南加州大学)

Nathanael Jo, Sina Aghaei, Andrés Gómez, Phebe Vayanos

AI总结:

提出混合整数优化框架学习最优公平分类树,引入决策复杂度度量,权衡可解释性、公平性与准确性,在固定差异阈值下可解释性代价约4.2个百分点,但能实现几乎完全公平。

摘要:

机器学习在高风险领域的日益普及——这些领域直接影响人们的生计——迫切需要对可解释、公平且高度准确的算法的需求。基于这些需求,我们提出了一个混合整数优化(MIO)框架,用于学习最优分类树——这是最具可解释性的模型之一——并可通过任意公平性约束进行增强。为了更好地量化“可解释性的代价”,我们还提出了一种新的模型可解释性度量,称为决策复杂度,该度量允许在不同类别的机器学习模型之间进行比较。我们将我们的方法与公平分类的先进方法在流行数据集上进行基准测试;在此过程中,我们进行了关于可解释性、公平性和预测准确性之间权衡的首批全面分析之一。在给定的差异阈值下,与表现最佳、复杂的模型相比,我们的方法在样本外准确性方面的可解释性代价约为4.2个百分点。然而,我们的方法始终能找到几乎完全平等的决策,而其他方法很少能做到这一点。

英文摘要:

The increasing use of machine learning in high-stakes domains -- where people's livelihoods are impacted -- creates an urgent need for interpretable, fair, and highly accurate algorithms. With these needs in mind, we propose a mixed integer optimization (MIO) framework for learning optimal classification trees -- one of the most interpretable models -- that can be augmented with arbitrary fairness constraints. In order to better quantify the "price of interpretability", we also propose a new measure of model interpretability called decision complexity that allows for comparisons across different classes of machine learning models. We benchmark our method against state-of-the-art approaches for fair classification on popular datasets; in doing so, we conduct one of the first comprehensive analyses of the trade-offs between interpretability, fairness, and predictive accuracy. Given a fixed disparity threshold, our method has a price of interpretability of about 4.2 percentage points in terms of out-of-sample accuracy compared to the best performing, complex models. However, our method consistently finds decisions with almost full parity, while other methods rarely do.

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。

↑