AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
复制标题
DOI：
10.1147/jrd.2019.2942287
复制
发表时间：
2019-07-01
影响因子：
1.3
通讯作者：
Zhang, Y.
中科院分区：
文献类型：
--
作者：
Bellamy, R. K. E.;Dey, K.;Zhang, Y.
随着机器学习模型被用于支持高风险应用（如抵押贷款、招聘和监狱判决）的决策制定，公平性成为一个越来越重要的问题。本文介绍了一个用于算法公平性的新的开源Python工具包，AI fairness 360 (AIF360)，它是在Apache v2.0许可下发布的（https://github.com/ibm/aif360）。该工具包的主要目标是帮助促进公平研究算法在工业环境中使用的过渡，并为公平研究人员提供共享和评估算法的通用框架。该软件包包括一套全面的数据集和模型的公平指标，对这些指标的解释，以及算法，以减轻数据集和模型的偏见。它还包括交互式web体验，为业务线用户、研究人员和开发人员提供了概念和功能的简要介绍，以便使用他们的新算法和改进来扩展工具包，并将其用于性能基准测试。内置的测试基础设施维护代码质量。
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This article introduces a new open-source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms for use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactiveWeb experience that provides a gentle introduction to the concepts and capabilities for line-of-business users, researchers, and developers to extend the toolkit with their new algorithms and improvements and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.