提出FairSense框架，模拟长期反馈循环中的公平性问题
FairSense: Long-Term Fairness Analysis of ML-Enabled Systems
- 基于蒙特卡洛仿真，追踪系统配置在动态环境中的演化轨迹
- 揭示短期公平的模型在长期可能引发严重不公平现象
- 适用于信贷、医疗和警务等高风险决策系统的公平性评估
机器学习模型的算法公平性近年来引发广泛关注。现有方法多聚焦静态场景下的公平性检测与缓解，但许多机器学习系统运行于动态环境中，其预测决策会反作用于环境，进而影响未来决策，形成自我强化的反馈循环，导致长期公平性问题。本文提出基于仿真的FairSense框架，用于检测和分析机器学习系统的长期不公平性。给定公平性要求后，FairSense通过蒙特卡洛模拟生成每种系统配置的演化路径，并对多种配置空间进行敏感性分析，以评估设计选项与环境因素对长期公平性的影响。我们在三个真实案例中验证了该框架的有效性：贷款发放、阿片类药物风险评分和预测性警务。
原文摘要 · Abstract (English)
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.
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。