The Challenge of Imputation in Explainable Artificial Intelligence Models
The Challenge of Imputation in Explainable Artificial Intelligence Models
复制标题
可解释的人工智能模型中插补的挑战
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
A. Teredesai
中科院分区：
文献类型：
--
作者：
M. Ahmad;C. Eckert;A. Teredesai
人工智能中的可解释模型经常被用来确保人工智能系统的透明度和问责制。解释的保真度取决于使用的算法以及数据的保真度。许多真实世界的数据集都有可能极大地影响解释保真度的缺失值。处理这类情况的标准方法是归责。然而，这可能导致推定的值可能对应于引用反事实的设置的情况。根据人工智能模型的解释采取行动可能会导致不安全的结果。在这篇文章中，我们探索了不同的环境，其中人工智能模型可能是有问题的，并描述了解决这些场景的方法。
Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many real world datasets have missing values that can greatly influence explanation fidelity. The standard way to deal with such scenarios is imputation. This can, however, lead to situations where the imputed values may correspond to a setting which refer to counterfactuals. Acting on explanations from AI models with imputed values may lead to unsafe outcomes. In this paper, we explore different settings where AI models with imputation can be problematic and describe ways to address such scenarios.