Bias analysis and mitigation in data-driven tools using provenance

Bias analysis and mitigation in data-driven tools using provenance
复制标题

使用来源进行数据驱动工具中的偏差分析和缓解

DOI:
10.1145/3530800.3534528
复制
发表时间:
2022
期刊:
TaPP '22: Proceedings of the 14th International Workshop on the Theory and Practice of Provenance
影响因子:
--
通讯作者:
Jagadish, H. V.
Jagadish, H. V.
中科院分区:
--
文献类型:
--
作者:
Moskovitch, Yuval;Li, Jinyang;Jagadish, H. V.

文献摘要

参考文献

被引文献

相似文献

近年来,数据驱动系统中的公平性和偏差缓解已经得到了广泛的研究。在本文中,我们提出了一种新的方法对公平性分析和偏见缓解利用出处的概念,这被证明是有用的类似的任务,在数据和过程分析的背景下。我们用一个简单的用例来说明这个想法,展示了一个减轻少数群体代表性不足所造成的偏见的场景。最后,我们概述了在数据驱动系统中开发基于出处的解决方案以进行偏差分析和缓解的机会和挑战。
Fairness and bias mitigation in data-driven systems has been extensively studied in recent years. In this paper, we suggest a novel approach towards fairness analysis and bias mitigation utilizing the notion of provenance, which was shown to be useful for similar tasks in the context of data and process analyses. We illustrate the idea using a simple use-case demonstrating a scenario of mitigating bias caused by inadequate minority group representation. We conclude with an outline of opportunities and challenges in developing provenance-based solutions for bias analysis and mitigation in data-driven systems.
关于检测精挑细选的概括
DOI: 10.14778/3485450.3485457
发表时间: 2021
期刊: Proc. VLDB Endow.
影响因子: --
作者:
Yin Lin;Brit Youngmann;Y. Moskovitch;H. V. Jagadish;Tova Milo
通讯作者: Tova Milo
本机机器学习管道中数据预处理的轻量级检查
DOI: --
发表时间: 2021
期刊: Conference on Innovative Data Systems Research (CIDR
影响因子: --
作者:
Grafberger, Stefan;Stoyanovich, Julia;Schelter, Sebastian
通讯作者: Schelter, Sebastian
DOI: --
发表时间: 2020
期刊: SIGMOD Conference
影响因子: --
作者:
P. Bourhis;Daniel Deutch;Y. Moskovitch
通讯作者: Y. Moskovitch
PrIU:一种基于来源的增量更新回归模型的方法
DOI: 10.1145/3318464.3380571
发表时间: 2020
期刊: ISBN 978-1-4503-6735-6
影响因子: --
作者:
Wu, Yinjun;Tannen, Val;Davidson, Susan
通讯作者: Davidson, Susan