Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach
Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach
复制标题
DOI：
10.1609/aaai.v35i11.17193
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Cuong Tran;Ferdinando Fioretto;Pascal Van Hentenryck
中科院分区：
文献类型：
--
作者：
Cuong Tran;Ferdinando Fioretto;Pascal Van Hentenryck
数据驱动决策的关键是建立模型，其成果不会歧视某些人口统计群体，包括性别，种族或年龄，以确保在学习任务中的不歧视，对敏感属性的了解是必不可少的实际上，由于法律和道德要求，这些属性可能无法解决这一挑战在差异隐私的通知和使用拉格朗日双重性来设计中性网络的情况下，可以适应公平限制，同时保证敏感属性的隐私分析。关于几个预测任务的拟议模型。
A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the sensitive attributes is essential, while, in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of the individuals’ sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints while guaranteeing the privacy of sensitive attributes. The paper analyses the tension between accuracy, privacy, and fairness and the experimental evaluation illustrates the benefits of the proposed model on several prediction tasks.