Seldonian Toolkit: Building Software with Safe and Fair Machine Learning
Seldonian Toolkit: Building Software with Safe and Fair Machine Learning
复制标题
DOI：
10.1109/icse-companion58688.2023.00035
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Austin Hoag;James E. Kostas;B. C. Silva;P. Thomas;Yuriy Brun
中科院分区：
文献类型：
--
作者：
Austin Hoag;James E. Kostas;B. C. Silva;P. Thomas;Yuriy Brun
我们提出了Seldonian Toolkit，它使软件工程师能够将可证明安全和公平的机器学习算法集成到他们的系统中。使用数据和机器学习的软件系统通常部署在医疗应用、自动驾驶汽车、刑事司法系统和招聘流程等广泛的环境中。然而，这些系统可能会产生不安全和不公平的行为，例如建议可能致命的医疗，做出种族主义或性别歧视的预测，或促进激进和两极分化。为了减少这些不良行为，软件工程师需要能够轻松地将其基于机器学习的系统与领域专家（如医生和招聘经理）定义的特定领域的安全和公平要求相集成。Seldonian Toolkit提供了特殊的机器学习算法，使软件工程师能够将专家定义的安全性和公平性要求纳入他们的系统中，同时可证明地保证这些要求得到满足。有关Seldonian Toolkit的演示视频，请访问https://youtu.be/wHR-hDm9jX4/
We present the Seldonian Toolkit, which enables software engineers to integrate provably safe and fair machine learning algorithms into their systems. Software systems that use data and machine learning are routinely deployed in a wide range of settings from medical applications, autonomous vehicles, the criminal justice system, and hiring processes. These systems, however, can produce unsafe and unfair behavior, such as suggesting potentially fatal medical treatments, making racist or sexist predictions, or facilitating radicalization and polarization. To reduce these undesirable behaviors, software engineers need the ability to easily integrate their machine-learning-based systems with domain-specific safety and fairness requirements defined by domain experts, such as doctors and hiring managers. The Seldonian Toolkit provides special machine learning algorithms that enable software engineers to incorporate such expert-defined requirements of safety and fairness into their systems, while provably guaranteeing those requirements will be satisfied. A video demonstrating the Seldonian Toolkit is available at https://youtu.be/wHR-hDm9jX4/