arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.06764cs.LGcs.AIcs.CY
收藏

培训博览会神经网络的技术挑战

Technical Challenges for Training Fair Neural Networks

University of Maryland, College Park(马里兰大学帕克分校);Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所)

Valeriia Cherepanova, Vedant Nanda, Micah Goldblum, John P. Dickerson, Tom Goldstein

摘要:

随着机器学习算法在应用程序中的广泛部署,人们对其预测的公平性提出了许多担忧,特别是在高风险环境中(如面部识别和医学成像)。为了回应这些关注,社会提出并正式确定了各种公平的概念以及纠正不公平行为的方法。虽然公平性约束已经被广泛研究了经典模型,但对深度神经网络施加公平性的方法的有效性尚不清楚。在本文中,我们观察到这些大型模型过度拟合公平目标,并产生一系列意想不到的和不希望的后果。我们使用最先进的架构对面部识别和自动医疗诊断数据集进行实验。

英文摘要:

As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To respond to these concerns, the community has proposed and formalized various notions of fairness as well as methods for rectifying unfair behavior. While fairness constraints have been studied extensively for classical models, the effectiveness of methods for imposing fairness on deep neural networks is unclear. In this paper, we observe that these large models overfit to fairness objectives, and produce a range of unintended and undesirable consequences. We conduct our experiments on both facial recognition and automated medical diagnosis datasets using state-of-the-art architectures.

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。

↑