把公平性当作运行时属性，动态监测和调控AI决策偏差。
Algorithmic Fairness: A Runtime Perspective
- 用可变偏倚的抛硬币模型模拟实时决策序列，研究公平性动态变化。
- 提出适配环境演化、预测周期与置信度的监控与调控策略框架。
- 适用于需要持续公平性保障的实时系统，如信贷审批、招聘筛选。
人工智能公平性传统上被视作在固定数据集上一次性评估的静态属性。然而，现实中的AI系统是连续运行的，其结果与环境随时间演进。本文提出一种将公平性视为运行时属性的分析框架。基于一个最小但表达力强的模型——具有可能变化偏倚的抛硬币序列，研究了对投掷结果或硬币偏倚所表达的公平性进行监控与调控的问题。由于不存在适用于所有场景的通用解法，本文总结了监控与调控策略，参数化于环境动态、预测周期和置信阈值。针对两类问题，在简单或最小假设下给出通用结论。同时，梳理了马尔可夫与加性动态下的监控现有方案，以及已知动态下静态设定的调控现有方法。
原文摘要 · Abstract (English)
Fairness in AI is traditionally studied as a static property evaluated once, over a fixed dataset. However, real-world AI systems operate sequentially, with outcomes and environments evolving over time. This paper proposes a framework for analysing fairness as a runtime property. Using a minimal yet expressive model based on sequences of coin tosses with possibly evolving biases, we study the problems of monitoring and enforcing fairness expressed in either toss outcomes or coin biases. Since there is no one-size-fits-all solution for either problem, we provide a summary of monitoring and enforcement strategies, parametrised by environment dynamics, prediction horizon, and confidence thresholds. For both problems, we present general results under simple or minimal assumptions. We survey existing solutions for the monitoring problem for Markovian and additive dynamics, and existing solutions for the enforcement problem in static settings with known dynamics.
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。