针对稀有事件解释可靠性，提出一种评估方法
Assessing reliability of explanations in unbalanced datasets: a use-case on the occurrence of frost events
- 聚焦少数类样本，通过邻域生成与解释聚合评估
- 在霜冻事件数据集上验证了解释一致性提升
- 适合高风险场景下需可信解释的AI应用
可解释人工智能（XAI）在实际应用中日益重要，尤其在近年立法要求背景下。然而解释的鲁棒性常被忽视，而这是信任解释的基础。本研究针对高风险场景中常见的不平衡数据集，提出一种面向少数类的简单评估方法，结合流形内邻域生成、解释聚合及一致性度量，以评估解释可靠性。实验基于一个包含数值特征的表格数据集，分析霜冻事件的发生情况。
原文摘要 · Abstract (English)
The usage of eXplainable Artificial Intelligence (XAI) methods has become essential in practical applications, given the increasing deployment of Artificial Intelligence (AI) models and the legislative requirements put forward in the latest years. A fundamental but often underestimated aspect of the explanations is their robustness, a key property that should be satisfied in order to trust the explanations. In this study, we provide some preliminary insights on evaluating the reliability of explanations in the specific case of unbalanced datasets, which are very frequent in high-risk use-cases, but at the same time considerably challenging for both AI models and XAI methods. We propose a simple evaluation focused on the minority class (i.e. the less frequent one) that leverages on-manifold generation of neighbours, explanation aggregation and a metric to test explanation consistency. We present a use-case based on a tabular dataset with numerical features focusing on the occurrence of frost events.
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。