arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08485cs.AIcs.CY
收藏

公平性能否自动化?公平感知AutoML的指南与机遇

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

Eindhoven University of Technology(埃因霍温理工大学);Ludwig-Maximilians-Universität München(慕尼黑大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Albert-Ludwigs-Universität Freiburg(阿尔伯特-路德维希-弗莱堡大学);University of Tübingen(蒂宾根大学)

Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Edward Bergman, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter

AI总结:

本文探讨公平性无法完全自动化,系统梳理公平性相关伤害的来源及其对公平感知AutoML设计的影响,指出公平感知AutoML可作为ML从业者的重要工具,并提出开放性技术挑战与以用户为中心的辅助系统设计方向。

摘要:

自动化机器学习(AutoML)领域引入了自动化机器学习(ML)系统开发部分环节的技术,加速了开发过程并降低了初学者的门槛。然而,源自ML模型的决策可能会在社会中再现、放大甚至引入不公平性,从而对(群体中的)个体造成伤害。作为回应,研究人员已开始提出能够联合优化公平性与预测性能的AutoML系统,以减轻与公平性相关的伤害。然而,公平性是一个复杂且本质上具有跨学科性质的课题,仅仅将其表述为一个优化问题可能会产生不利的副作用。通过本项工作,我们旨在提高AutoML系统开发者对公平感知AutoML此类局限性的认识,同时呼吁关注AutoML作为公平性研究工具的潜力。我们全面概述了公平性相关伤害可能产生的不同方式,以及由此对公平感知AutoML设计带来的影响。我们得出结论:尽管公平性无法被自动化,但公平感知AutoML可以在ML从业者的工具箱中发挥重要作用。我们着重指出了未来在这一方向上工作的若干开放性技术挑战。此外,我们倡导创建更多以用户为中心的辅助系统,旨在解决公平性工作中遇到的挑战。

英文摘要:

The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can reproduce, amplify, or even introduce unfairness in our societies, causing harm to (groups of) individuals. In response, researchers have started to propose AutoML systems that jointly optimize fairness and predictive performance to mitigate fairness-related harm. However, fairness is a complex and inherently interdisciplinary subject, and solely posing it as an optimization problem can have adverse side effects. With this work, we aim to raise awareness among developers of AutoML systems about such limitations of fairness-aware AutoML, while also calling attention to the potential of AutoML as a tool for fairness research. We present a comprehensive overview of different ways in which fairness-related harm can arise and the ensuing implications for the design of fairness-aware AutoML. We conclude that while fairness cannot be automated, fairness-aware AutoML can play an important role in the toolbox of ML practitioners. We highlight several open technical challenges for future work in this direction. Additionally, we advocate for the creation of more user-centered assistive systems designed to tackle challenges encountered in fairness work

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。

↑