arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04339cs.LG
收藏

RISE: 机器学习模型中公平性的交互式可视化诊断

RISE: Interactive Visual Diagnosis of Fairness in Machine Learning Models

University of Florida(佛罗里达大学)

Ray Chen, Christan Grant

AI总结:

RISE通过交互式可视化工具帮助诊断机器学习模型中的公平性问题,揭示准确率与公平性的权衡,支持更明智的模型选择。

摘要:

在域转移下评估公平性具有挑战性,因为标量指标往往掩盖了不平等的确切出现位置和方式。我们介绍了RISE(通过排序评估进行残差检查),一种交互式可视化工具,将排序残差转换为可解释的模式。通过将残差曲线结构与正式公平性概念联系起来,RISE实现了局部不平等诊断、跨环境的子群体比较以及隐藏公平性问题的检测。通过事后分析,RISE揭示了聚合统计信息所遗漏的准确率-公平性权衡,支持更明智的模型选择。

英文摘要:

Evaluating fairness under domain shift is challenging because scalar metrics often obscure exactly where and how disparities arise. We introduce \textit{RISE} (Residual Inspection through Sorted Evaluation), an interactive visualization tool that converts sorted residuals into interpretable patterns. By connecting residual curve structures to formal fairness notions, RISE enables localized disparity diagnosis, subgroup comparison across environments, and the detection of hidden fairness issues. Through post-hoc analysis, RISE exposes accuracy-fairness trade-offs that aggregate statistics miss, supporting more informed model selection.

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。

↑