[论文解读] Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges

Songül Tolan|arXiv (Cornell University)|Jan 15, 2019

Ethics and Social Impacts of AI被引用 41

一句话总结

对算法决策中的公平性进行批判性综述，强调界定公平性的复杂性、统计标准的局限性，以及对领域特定约束、透明度和审计的需求。

ABSTRACT

Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their decisions solely on facts and remain unaffected by human cognitive biases, discriminatory tendencies or emotions. Yet, there is overwhelming evidence showing that algorithms can inherit or even perpetuate human biases in their decision making when they are based on data that contains biased human decisions. This has led to a call for fairness-aware machine learning. However, fairness is a complex concept which is also reflected in the attempts to formalize fairness for algorithmic decision making. Statistical formalizations of fairness lead to a long list of criteria that are each flawed (or harmful even) in different contexts. Moreover, inherent tradeoffs in these criteria make it impossible to unify them in one general framework. Thus, fairness constraints in algorithms have to be specific to the domains to which the algorithms are applied. In the future, research in algorithmic decision making systems should be aware of data and developer biases and add a focus on transparency to facilitate regular fairness audits.

研究动机与目标

• 解释为何在敏感领域的机器学习会从数据和决策中继承偏见。
• 调查现有的公平性标准及其在不同情境中的局限性。
• 论证公平性约束必须针对具体领域进行定制，而不能统一为单一框架。
• 强调透明度和定期公平性审计以解决数据和开发者偏见的重要性。

提出的方法

• 综述并综合关于公平感知机器学习及其形式化的文献。
• 讨论在不同情境中统计公平性标准的局限性与权衡。
• 提出针对领域的公平性约束与基于透明度的治理的论点。

实验结果

研究问题

• RQ1 在不同应用领域中，标准统计公平性的局限性是什么？
• RQ2 数据与开发者偏见如何影响算法决策，以及透明度如何促进审计？
• RQ3 为何公平性约束必须是情境特定的，而不能在所有设置中普遍统一？

主要发现

• 公平性标准繁多且常常存在缺陷，权衡使得难以形成单一的普遍框架。
• 当在有偏见的数据或决策上训练时，算法可能编码并放大人类偏见。
• 公平性约束应针对应用领域定制，才能有意义且有效。
• 未来工作应强调透明度，以促进定期的公平性审计。
• 提高对数据和开发者偏见的认识对于推动公平决策至关重要。