DALE：差分累积局部效应，用于高效准确的全局解释
DALE: Differential Accumulated Local Effects for efficient and accurate global explanations
摘要：
累积局部效应（ALE）是一种用于准确估计特征效应的方法，克服了先前存在的方法（如部分相关图）的基本失效模式。然而，ALE的近似，即用于从训练集的有限样本估计ALE的方法，面临两个弱点。首先，它在输入具有高维度的情况下不能很好地扩展，其次，当训练集相对较小时，它容易受到分布外（OOD）采样的影响。在本文中，我们提出了一种新的ALE近似，称为差分累积局部效应（DALE），它可以用于ML模型可微且可访问自动可微框架的情况。我们的建议具有显着的计算优势，使特征效果估计适用于高维机器学习的情况下，计算开销接近零。此外，DALE不创建用于计算特征效应的人工点，解决了由于OOD采样而导致的误导性估计。最后，我们正式证明，在一定的假设下，DALE是一个无偏估计的ALE，我们提出了一种方法来量化的标准误差的解释。使用合成和真实数据集的实验证明了所提出的方法的价值。
英文摘要：
Accumulated Local Effect (ALE) is a method for accurately estimating feature effects, overcoming fundamental failure modes of previously-existed methods, such as Partial Dependence Plots. However, ALE's approximation, i.e. the method for estimating ALE from the limited samples of the training set, faces two weaknesses. First, it does not scale well in cases where the input has high dimensionality, and, second, it is vulnerable to out-of-distribution (OOD) sampling when the training set is relatively small. In this paper, we propose a novel ALE approximation, called Differential Accumulated Local Effects (DALE), which can be used in cases where the ML model is differentiable and an auto-differentiable framework is accessible. Our proposal has significant computational advantages, making feature effect estimation applicable to high-dimensional Machine Learning scenarios with near-zero computational overhead. Furthermore, DALE does not create artificial points for calculating the feature effect, resolving misleading estimations due to OOD sampling. Finally, we formally prove that, under some hypotheses, DALE is an unbiased estimator of ALE and we present a method for quantifying the standard error of the explanation. Experiments using both synthetic and real datasets demonstrate the value of the proposed approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
