用可视化工具发现模型在不同场景下的公平性问题
RISE: Interactive Visual Diagnosis of Fairness in Machine Learning Models
- 将残差排序后转为可解释的模式图
- 能定位不公平现象出现的具体子群体和场景
- 适合关注模型公平性的研究人员与工程师
在领域偏移下评估公平性极具挑战，因为标量指标常掩盖了偏差发生的具体位置与方式。我们提出交互式可视化工具 RISE（通过排序评估进行残差检测），将排序后的残差转化为可解释的模式。通过将残差曲线结构与正式的公平性概念关联，RISE 能实现局部偏差诊断、跨环境子群体比较，并发现隐藏的公平性问题。事后分析揭示了聚合统计量所忽略的准确率-公平性权衡，有助于更明智的模型选择。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。