FairLay-ML：数据驱动的社会关键型软件中公平性的直观调试
FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software
AI总结：
FairLay-ML是一个面向数据驱动软件的公平性调试工具，通过可视化数据、模型与决策逻辑、训练多组公平性-准确性权衡模型并结合反事实测试，帮助开发者和最终用户发现并解释公平性缺陷。
摘要：
数据驱动的软件解决方案已被广泛用于具有重大社会经济、法律和伦理影响的关键领域。然而，数据驱动解决方案的快速采用对自动化决策支持软件的可信度构成了重大威胁。开发人员对解决方案的理解不足以及数据集中的历史和当前偏见是主要挑战。为了帮助数据驱动软件的开发人员和最终用户，我们提出了FairLay-ML，这是一种调试工具，用于测试和解释数据驱动解决方案的公平性影响。FairLay-ML可视化数据集、训练模型以及给定数据点的决策逻辑。此外，它训练了多种具有不同公平性-准确性权衡的模型。关键是，FairLay-ML结合了反事实公平性测试，能够发现开发数据集之外的缺陷。我们通过FairLay-ML进行了两项研究，使我们能够测量主流反事实测试中的假阳性/假阴性，并通过课堂调查理解人类对反事实测试用例的感知。FairLay-ML及其基准测试已公开发布于https://github.com/Pennswood/FairLay-ML。该工具的在线版本可在https://fairlayml-v2.streamlit.app/获取。我们在https://youtu.be/wNI9UWkywVU?t=133提供了该工具的视频演示。
英文摘要：
Data-driven software solutions have significantly been used in critical domains with significant socio-economic, legal, and ethical implications. The rapid adoptions of data-driven solutions, however, pose major threats to the trustworthiness of automated decision-support software. A diminished understanding of the solution by the developer and historical/current biases in the data sets are primary challenges. To aid data-driven software developers and end-users, we present FairLay-ML, a debugging tool to test and explain the fairness implications of data-driven solutions. FairLay-ML visualizes the logic of datasets, trained models, and decisions for a given data point. In addition, it trains various models with varying fairness-accuracy trade-offs. Crucially, FairLay-ML incorporates counterfactual fairness testing that finds bugs beyond the development datasets. We conducted two studies through FairLay-ML that allowed us to measure false positives/negatives in prevalent counterfactual testing and understand the human perception of counterfactual test cases in a class survey. FairLay-ML and its benchmarks are publicly available at https://github.com/Pennswood/FairLay-ML. The live version of the tool is available at https://fairlayml-v2.streamlit.app/. We provide a video demo of the tool at https://youtu.be/wNI9UWkywVU?t=133.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
