Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey
Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey
复制标题
DOI：
10.1145/3631326
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Max Hort;Zhenpeng Chen;J Zhang;Federica Sarro;M. Harman
中科院分区：
文献类型：
--
作者：
Max Hort;Zhenpeng Chen;J Zhang;Federica Sarro;M. Harman
本文对机器学习(ML)模型中实现公平的偏差缓解方法进行了全面的综述。我们总共收集了341篇关于ML分类器的偏向缓解的出版物。这些方法可以根据它们的干预程序(即，前处理、中处理、后处理)和它们所采用的技术来区分。我们调查了现有的偏差缓解方法是如何在文献中进行评估的。特别是，我们考虑了数据集、指标和基准测试。根据收集到的见解(例如，最流行的公平衡量标准是什么？有多少数据集被用于评估偏差缓解方法？)，我们希望在开发和评估新的偏差缓解方法时支持实践者做出明智的选择。
This article provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning bias mitigation for ML classifiers. These methods can be distinguished based on their intervention procedure (i.e., pre-processing, in-processing, post-processing) and the technique they apply. We investigate how existing bias mitigation methods are evaluated in the literature. In particular, we consider datasets, metrics, and benchmarking. Based on the gathered insights (e.g., What is the most popular fairness metric? How many datasets are used for evaluating bias mitigation methods?), we hope to support practitioners in making informed choices when developing and evaluating new bias mitigation methods.