Leave-one-out Unfairness
Leave-one-out Unfairness
复制标题
DOI：
10.1145/3442188.3445894
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Emily Black;Matt Fredrikson
中科院分区：
文献类型：
--
作者：
Emily Black;Matt Fredrikson
我们介绍了一项不公平的不公平，这是由于模型对个人的预测可能会改变或删除模型中其他人的培训数据，这将变化。一对一的不公平吸引了公正决定不是任意的想法：它们不应基于任何一个人包含在培训数据中的机会事件。一对一的不公平性与算法稳定性密切相关，但它重点是单个点对单位变化对训练数据的预测结果的一致性，而不是汇总模型的错误。除了正式化一对一的不公平之外，我们还表征了深层模型在多大程度上不公平地对真实数据进行保留的程度，包括在概括误差很小的情况下。此外，我们证明了对抗性训练和随机平滑技术对剩余的公平性具有相反的影响，这阐明了在深层模型中稳健性，记忆，个人公平和一对一的公平性之间的关系。最后，我们讨论可能会受到一对一不公平影响的显着实用应用。
We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. Leave-one-out unfairness appeals to the idea that fair decisions are not arbitrary: they should not be based on the chance event of any one person's inclusion in the training data. Leave-one-out unfairness is closely related to algorithmic stability, but it focuses on the consistency of an individual point's prediction outcome over unit changes to the training data, rather than the error of the model in aggregate. Beyond formalizing leave-one-out unfairness, we characterize the extent to which deep models behave leave-one-out unfairly on real data, including in cases where the generalization error is small. Further, we demonstrate that adversarial training and randomized smoothing techniques have opposite effects on leave-one-out fairness, which sheds light on the relationships between robustness, memorization, individual fairness, and leave-one-out fairness in deep models. Finally, we discuss salient practical applications that may be negatively affected by leave-one-out unfairness.