快速生成带置信度的模型解释，适合实时高风险场景。
Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models
- 结合扰动技术提升解释速度，保持局部重要性与不确定性量化。
- 在保证置信度的前提下实现显著加速，适用于分类与阈值回归。
- 适合需要实时响应且需评估不确定性的关键应用。
本文提出Fast Calibrated Explanations，一种用于机器学习模型的快速、带不确定性感知的解释方法。通过将ConformaSight中的扰动技术融入校准解释（CE）的核心组件——局部特征重要性与校准预测中，实现了显著提速。该方法在牺牲少量细节的情况下，仍保留不确定性量化能力。适用于分类与阈值回归任务，可提供目标值高于或低于用户定义阈值的概率。该方法保持了CE在分类与概率回归中的通用性，特别适合对不确定性量化有严格要求的预测任务。
原文摘要 · Abstract (English)
This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbation techniques from ConformaSight - a global explanation framework - into the core elements of Calibrated Explanations (CE), we achieve significant speedups. These core elements include local feature importance with calibrated predictions, both of which retain uncertainty quantification. While the new method sacrifices a small degree of detail, it excels in computational efficiency, making it ideal for high-stakes, real-time applications. Fast Calibrated Explanations are applicable to probabilistic explanations in classification and thresholded regression tasks, where they provide the likelihood of a target being above or below a user-defined threshold. This approach maintains the versatility of CE for both classification and probabilistic regression, making it suitable for a range of predictive tasks where uncertainty quantification is crucial.
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。