提出不确定性感知的可解释AI框架，提升电力扰动分类的解释可靠性。
A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
- 用采样模型生成解释分布，融合均值、离散度等统计量进行综合解释。
- 在15类电力扰动数据上，集成方法的平均遮蔽解释更贴合真实扰动区域。
- 适用于需要可信解释的工业级故障诊断场景，尤其关注噪声敏感性。
事后可解释AI方法通常仅输出单一归因图，即使模型参数存在不确定性。本文定义了‘解释分布’为从采样模型中获得的归因图集合。不确定性感知相关性归因算子（UA-RAO）通过均值、离散度、分位数和一致集总结该分布。理论分离了后验近似误差与有限样本误差，并考虑激活边界变化及随机解释器的影响。在15类电力质量扰动基准数据集上，深度集成模型的平均遮蔽解释比确定性基线更契合已知扰动区域，但改进效果依赖于扰动类型。通过控制输入失真测试发现，加性噪声对解释的影响大于幅值缩放或对齐的时间偏移。
原文摘要 · Abstract (English)
Post-hoc explainable AI (XAI) methods usually return one attribution map, even when the model represents uncertainty in its parameters. We define the \emph{explanation distribution} as the distribution of attribution maps obtained from sampled models. The uncertainty-aware relevance attribution operator (UA-RAO) summarises this distribution using the mean, dispersion, quantiles, and agreement sets. The theory separates posterior-approximation error from finite-sample error and accounts for changes across activation boundaries and for stochastic explainers. On a 15-class power-quality-disturbance benchmark, the mean occlusion explanation from a deep ensemble aligns better with known disturbance regions than the deterministic baseline, although the improvement depends on the disturbance type. Tests with controlled input distortions show that additive noise changes the explanations more than amplitude scaling or aligned temporal shifts.
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。