arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.01889cs.LGcs.CY
收藏

探索公平性:针对公平性定义的定制损失函数研究

Exploring Equality: An Investigation into Custom Loss Functions for Fairness Definitions

Gordon Lee, Simeon Sayer

AI总结:

本文首次将 Group Accuracy Parity 框架应用于 COMPAS,通过定制损失函数和 Pareto 前沿分析,证明其在公平性与准确性之间取得了比传统公平性定义更好的平衡,同时指出算法改进之外还需法律和制度变革。

摘要:

本文通过在 COMPAS 上构建以定制损失函数训练的神经网络,并针对特定公平性准则进行优化,探讨了各种公平性指标(如均等化几率、差别影响和机会均等)与预测准确性之间的复杂权衡。本文首次实现了 Gupta 等人(2024)从理论上提出的新型 Group Accuracy Parity(GAP)框架的公平性驱动版本,并将其应用于 COMPAS。为了操作化并准确比较针对不同公平性理想进行优化的 COMPAS 模型的公平性,本文开发并提出了一种组合分析程序,该程序结合了 Pareto 前沿和多元分析,并利用小提琴图等数据可视化方法。本文得出结论:与 COMPAS 当前的全国性实施以及针对更传统公平性定义进行优化的 COMPAS 替代实现相比,GAP 在公平性与准确性之间实现了更好的平衡。虽然本文对 COMPAS 的算法改进显著增强了其公平性,但外部偏见削弱了其实施的公平性。预测性警务等实践以及 COMPAS 内部运作缺乏透明度等问题,都加剧了该算法的历史性不公正。在 COMPAS 预测方法取得进展的同时,必须进行法律和制度层面的变革,才能实现 COMPAS 的公正部署。

英文摘要:

This paper explores the complex tradeoffs between various fairness metrics such as equalized odds, disparate impact, and equal opportunity and predictive accuracy within COMPAS by building neural networks trained with custom loss functions optimized to specific fairness criteria. This paper creates the first fairness-driven implementation of the novel Group Accuracy Parity (GAP) framework, as theoretically proposed by Gupta et al. (2024), and applies it to COMPAS. To operationalize and accurately compare the fairness of COMPAS models optimized to differing fairness ideals, this paper develops and proposes a combinatory analytical procedure that incorporates Pareto front and multivariate analysis, leveraging data visualizations such as violin graphs. This paper concludes that GAP achieves an enhanced equilibrium between fairness and accuracy compared to COMPAS's current nationwide implementation and alternative implementations of COMPAS optimized to more traditional fairness definitions. While this paper's algorithmic improvements of COMPAS significantly augment its fairness, external biases undermine the fairness of its implementation. Practices such as predictive policing and issues such as the lack of transparency regarding COMPAS's internal workings have contributed to the algorithm's historical injustice. In conjunction with developments regarding COMPAS's predictive methodology, legal and institutional changes must happen for COMPAS's just deployment.

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。

↑