[论文解读] AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

Rachel Bellamy, Kuntal Dey+16 more|arXiv (Cornell University)|Oct 3, 2018

Ethics and Social Impacts of AI参考文献 18被引用 265

一句话总结

介绍 AI Fairness 360（AIF360），一个开源的 Python 工具包，提供偏见检测指标、解释和缓解算法，以及用于工业可用性和基准测试的交互式网页界面。

ABSTRACT

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 paper 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 to 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 interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable 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.

研究动机与目标

• 促进对机器学习中公平性指标和缓解技术的理解。
• 提供一个开放、可扩展的平台，供研究人员和业界分享和基准测试公平性算法。
• 通过可用的工具和文档，促进公平性研究向工业实践的转化。

提出的方法

• 定义一个可扩展的体系结构，包含数据集表示、指标、解释器和偏见缓解算法。
• 整合 71+ 偏见检测指标、9 种偏见缓解方法，以及一个指标解释框架。
• 提供一个标准流程（数据集 -> 公平数据集 -> 模型 -> 预测），在多个阶段评估偏见。
• 开发基于网络的交互体验和广泛的文档，以帮助从业者。
• 实现严格的测试与持续集成设置，以维护代码质量。

实验结果

研究问题

• RQ1 一个统一的开源工具包如何在不同数据集和模型中支持检测、理解和缓解算法偏见？
• RQ2 在不同的公平性定义和部署情境下，哪些指标和缓解策略最有效？
• RQ3 解释和偏见定位（在受保护属性和特征中的偏见）如何帮助用户选择合适的干预措施？

主要发现

• AIF360 将偏见指标、缓解算法和解释整合在一个开源包中，以促进基准测试和采用。
• 预处理和在处理中方法（例如 Reweighing、Optimized Pre-processing、Adversarial Debiasing）通常在不同数据集上对准确率有不同影响的同时改善公平性指标。
• 后处理方法（如 Equalized Odds、Calibrated Equalized Odds、Reject Option）在无法重新训练模型时提供替代方案，存在准确性和公平性之间的权衡。
• 一个交互式网页体验和大量教程支持商业用户、开发者和研究人员将该工具包应用于现实世界的问题。