比较解析与经验方法，量化XAI中不确定性传播效果
Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators
- 提出统一框架，分析输入与模型参数扰动对解释的影响
- 实验证明部分XAI方法无法可靠传播不确定性
- 适合关注可信AI决策的科研与工程人员参考
理解可解释人工智能（XAI）中的不确定性对于建立信任和确保机器学习模型的可靠决策至关重要。本文提出一个统一框架，通过定义通用解释函数 $e_θ(x, f)$ 来量化和解释不确定性传播，涵盖输入数据扰动与模型参数变化等关键来源。采用解析与经验两种方式估计解释方差，系统评估不确定性对解释的影响。以一阶不确定性传播为例进行解析估算，在异构数据集上对比两类估计方法并检验其鲁棒性。实验揭示了现有XAI方法在解释不一致性上的局限，表明其未能有效捕捉和传播不确定性。研究强调高风险应用中需具备不确定性感知的解释能力，并为当前XAI方法的缺陷提供新洞见。实验代码已开源至 https://github.com/TeodorChiaburu/UXAI。
原文摘要 · Abstract (English)
Understanding uncertainty in Explainable AI (XAI) is crucial for building trust and ensuring reliable decision-making in Machine Learning models. This paper introduces a unified framework for quantifying and interpreting Uncertainty in XAI by defining a general explanation function $e_θ(x, f)$ that captures the propagation of uncertainty from key sources: perturbations in input data and model parameters. By using both analytical and empirical estimates of explanation variance, we provide a systematic means of assessing the impact uncertainty on explanations. We illustrate the approach using a first-order uncertainty propagation as the analytical estimator. In a comprehensive evaluation across heterogeneous datasets, we compare analytical and empirical estimates of uncertainty propagation and evaluate their robustness. Extending previous work on inconsistencies in explanations, our experiments identify XAI methods that do not reliably capture and propagate uncertainty. Our findings underscore the importance of uncertainty-aware explanations in high-stakes applications and offer new insights into the limitations of current XAI methods. The code for the experiments can be found in our repository at https://github.com/TeodorChiaburu/UXAI
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。