Label Denoising and Counterfactual Explanation with A Plug and Play Framework
Label Denoising and Counterfactual Explanation with A Plug and Play Framework
复制标题
DOI：
10.1109/bigdata55660.2022.10020488
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Wenting Qi;C. Chelmis
中科院分区：
文献类型：
--
作者：
Wenting Qi;C. Chelmis
大多数监督分类方法都假设有完美的训练数据，尽管在现实世界中通常不是这样。与此同时，反事实数据生成方法已经出现，作为对分类模型做出的决定提供事后解释的一种方式。然而，这些方法高度依赖于分类模型的输出，因为不同的输出会导致替代的，甚至是相互矛盾的解释。这项工作提出了一个即插即用的框架，用于在有噪声标记数据存在的情况下学习稳健的分类模型，并为给定分类模型做出的不良决策（例如，拒绝贷款申请）提供可操作的建议。通过考虑可选的噪声标签检测和反事实解释方法以及多种监督分类模型，证明了该框架的泛化性。使用三个基准数据集证明了该框架相对于几个基线的优越性。
Most supervised classification methods assume perfect training data, although this is not usually the case in the real–world. Meanwhile, counterfactual data generation approaches have emerged as a way to provide post–hoc explanation of decisions made by classification models. However, such approaches highly rely on the classification model output since different outputs lead to alternative, or even contradicting explanations. This work proposes a plug–and–play framework to learn a robust classification model in the presence of noisy labeled data and provide actionable suggestions for undesirable decisions (e.g., loan application rejection) made by a given classification model. The framework’s generalizability is demonstrated by considering alternative noisy label detection and counterfactual explanation methods, as well as diverse supervised classification models. The framework’s superiority against several baselines is demonstrated using three benchmark datasets.