Learning Unbiased Representations via Rényi Minimization

Learning Unbiased Representations via Rényi Minimization
复制标题

通过 Rényi 最小化学习无偏表示

DOI:
10.1007/978-3-030-86520-7_46
复制
发表时间:
2020
期刊:
ArXiv
影响因子:
--
通讯作者:
Marcin Detyniecki
Marcin Detyniecki
中科院分区:
--
文献类型:
--
作者:
Vincent Grari;Oualid El Hajouji;S. Lamprier;Marcin Detyniecki

文献摘要

参考文献

被引文献

相似文献

近年来,已经完成了重大工作,以在机器学习算法的培训目标中包括公平限制。许多最先进的算法通过学习公平代表性来应对这一挑战,该公平表示可以捕获所有相关信息以预测输出y,同时不包含有关敏感属性的任何信息。通过Hirschfeld-Gebelein-Renyi(HGR)最大相关系数的表示。我们利用最近的工作来通过学习深层神经网络转换来估算该系数,并将其用作Minmax游戏,以惩罚多维潜在表示中的内在偏见。与其他依赖性度量相比,HGR系数捕获了具有敏感变量的非线性依赖性的更多信息,从而使算法在减轻表示中的偏差方面更有效。我们经验评估和比较我们的方法,并证明了对该领域现有作品的重大改进。
In recent years, significant work has been done to include fairness constraints in the training objective of machine learning algorithms. Many state-of the-art algorithms tackle this challenge by learning a fair representation which captures all the relevant information to predict the output Y while not containing any information about a sensitive attribute S. In this paper, we propose an adversarial algorithm to learn unbiased representations via the Hirschfeld-Gebelein-Renyi (HGR) maximal correlation coefficient. We leverage recent work which has been done to estimate this coefficient by learning deep neural network transformations and use it as a minmax game to penalize the intrinsic bias in a multi dimensional latent representation. Compared to other dependence measures, the HGR coefficient captures more information about the non-linear dependencies with the sensitive variable, making the algorithm more efficient in mitigating bias in the representation. We empirically evaluate and compare our approach and demonstrate significant improvements over existing works in the field.
视而不见:显式消除深度神经网络嵌入的偏差和变异
DOI: 10.48550/arxiv.1809.02169
发表时间: 2018
期刊: arXiv e-prints
影响因子: --
作者:
Alvi Mohsan
通讯作者: Alvi Mohsan
DOI: 10.1007/s10994-008-5085-3
发表时间: 2009-01-01
期刊: MACHINE LEARNING
影响因子: 7.5
作者:
Hardoon, David R.;Shawe-Taylor, John
通讯作者: Shawe-Taylor, John