FairSense:面向机器学习使能系统的长期公平性分析
FairSense: Long-Term Fairness Analysis of ML-Enabled Systems
AI总结:
本文提出基于仿真的框架FairSense,通过蒙特卡洛仿真和敏感性分析检测ML使能系统中由反馈回路引起的长期不公平性,并在贷款、阿片类药物风险评分和预测性警务三个案例中验证其效用。
摘要:
近年来,机器学习(ML)模型的算法公平性引发了显著关注。许多测试、验证和偏差缓解技术被提出,用于识别和减少ML模型中的公平性问题。现有方法以模型为中心,旨在检测静态设置下的公平性问题。然而,许多ML使能系统运行在动态环境中,系统做出的预测决策会影响环境,而环境反过来又影响未来的决策。这种自我强化的反馈回路即使在即时结果是公平的情况下,也可能导致长期的公平性违规。在本文中,我们提出了一个基于仿真的框架FairSense,用于检测和分析ML使能系统中的长期不公平性。给定公平性需求,FairSense执行蒙特卡洛仿真,为每个系统配置枚举演化轨迹。然后,FairSense对可能配置空间进行敏感性分析,以理解设计选项和环境因素对系统长期公平性的影响。我们通过三个真实世界案例研究展示了FairSense的潜在效用:贷款发放、阿片类药物风险评分和预测性警务。
英文摘要:
Algorithmic fairness of machine learning (ML) models has raised significant concern in the recent years. Many testing, verification, and bias mitigation techniques have been proposed to identify and reduce fairness issues in ML models. The existing methods are model-centric and designed to detect fairness issues under static settings. However, many ML-enabled systems operate in a dynamic environment where the predictive decisions made by the system impact the environment, which in turn affects future decision-making. Such a self-reinforcing feedback loop can cause fairness violations in the long term, even if the immediate outcomes are fair. In this paper, we propose a simulation-based framework called FairSense to detect and analyze long-term unfairness in ML-enabled systems. Given a fairness requirement, FairSense performs Monte-Carlo simulation to enumerate evolution traces for each system configuration. Then, FairSense performs sensitivity analysis on the space of possible configurations to understand the impact of design options and environmental factors on the long-term fairness of the system. We demonstrate FairSense's potential utility through three real-world case studies: Loan lending, opioids risk scoring, and predictive policing.
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。