Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness-猫眼课题宝

DOI：

10.24963/ijcai.2020/61

发表时间：

2020-02

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Samuel Yeom;Matt Fredrikson

我们彻底改变了个体公平性的定义——不是在给定一个预先确定的度量标准的情况下确定一个模型的公平性，而是为一个给定的模型找到一个满足个体公平性的度量标准。这可以促进关于模型公平性的讨论，解决可能难以先验地指定一个合适的度量标准的问题。我们的贡献有两方面：首先，我们引入了最小度量的定义，并根据最小度量来描述模型的行为。其次，对于更复杂的模型，我们应用来自对抗鲁棒性的随机平滑机制，使其在给定的加权Lp度量下具有个体公平性。我们的实验表明，将线性模型的最小度量应用于更复杂的神经网络，可以在对效用影响很小的情况下带来有意义且可解释的公平性保证。

We turn the definition of individual fairness on its head - rather than ascertaining the fairness of a model given a predetermined metric, we find a metric for a given model that satisfies individual fairness. This can facilitate the discussion on the fairness of a model, addressing the issue that it may be difficult to specify a priori a suitable metric. Our contributions are twofold: First, we introduce the definition of a minimal metric and characterize the behavior of models in terms of minimal metrics. Second, for more complicated models, we apply the mechanism of randomized smoothing from adversarial robustness to make them individually fair under a given weighted Lp metric. Our experiments show that adapting the minimal metrics of linear models to more complicated neural networks can lead to meaningful and interpretable fairness guarantees at little cost to utility.

Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness

文献摘要

相似文献