当前位置: X-MOL 学术arXiv.cs.LG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study
arXiv - CS - Machine Learning Pub Date : 2020-03-13 , DOI: arxiv-2003.07680
Po-Ming Law, Sana Malik, Fan Du, Moumita Sinha

Machine learning models often make predictions that bias against certain subgroups of input data. When undetected, machine learning biases can constitute significant financial and ethical implications. Semi-automated tools that involve humans in the loop could facilitate bias detection. Yet, little is known about the considerations involved in their design. In this paper, we report on an interview study with 11 machine learning practitioners for investigating the needs surrounding semi-automated bias detection tools. Based on the findings, we highlight four considerations in designing to guide system designers who aim to create future tools for bias detection.

中文翻译:

设计用于半自动检测机器学习偏差的工具:一项访谈研究

机器学习模型通常会做出对某些输入数据子组有偏见的预测。如果未被发现,机器学习偏见可能会构成重大的财务和道德影响。涉及人的半自动化工具可以促进偏差检测。然而,人们对其设计中涉及的注意事项知之甚少。在本文中,我们报告了与 11 位机器学习从业者的访谈研究,以调查围绕半自动偏差检测工具的需求。基于这些发现,我们强调了设计中的四个考虑因素,以指导旨在创建未来偏差检测工具的系统设计人员。
更新日期:2020-03-19
down
wechat
bug