Fairness-Aware Neural Réyni Minimization for Continuous Features
Fairness-Aware Neural Réyni Minimization for Continuous Features
复制标题
连续特征的公平感知神经最小化
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Marcin Detyniecki
中科院分区：
文献类型：
--
作者：
Vincent Grari;Boris Ruf;S. Lamprier;Marcin Detyniecki
过去几年，学术界和社会对公平机器学习的兴趣急剧上升。虽然最近提出了许多公平的算法来解决离散变量的这一挑战，但对于连续变量，只有少数想法存在。本文的目的是保证回归模型的输出与任意给定的连续敏感变量之间具有一定的独立性。为此，我们使用Hirschfeld-Gebelein-Renyi （HGR）最大相关系数作为公平性度量。我们提出了两种最小化HGR系数的方法。首先，通过神经网络估计$chi^{2}$散度来降低HGR的上界。其次，通过对抗性神经网络结构直接最小化HGR。其思想是预测输出Y，同时最小化对抗神经网络找到预测HGR系数所需的估计变换的能力。我们以经验评估和比较我们的方法，并展示了在该领域先前提出的工作的重大改进。
The past few years have seen a dramatic rise of academic and societal interest in fair machine learning. While plenty of fair algorithms have been proposed recently to tackle this challenge for discrete variables, only a few ideas exist for continuous ones. The objective in this paper is to ensure some independence level between the outputs of regression models and any given continuous sensitive variables. For this purpose, we use the Hirschfeld-Gebelein-Renyi (HGR) maximal correlation coefficient as a fairness metric. We propose two approaches to minimize the HGR coefficient. First, by reducing an upper bound of the HGR with a neural network estimation of the $chi^{2}$ divergence. Second, by minimizing the HGR directly with an adversarial neural network architecture. The idea is to predict the output Y while minimizing the ability of an adversarial neural network to find the estimated transformations which are required to predict the HGR coefficient. We empirically assess and compare our approaches and demonstrate significant improvements on previously presented work in the field.
影响因子：
7.5
作者：
Hardoon, David R.;Shawe-Taylor, John
通讯作者：
Shawe-Taylor, John