DALE: Differential Accumulated Local Effects for efficient and accurate global explanations

TL;DR

DALE introduces a novel, efficient method for estimating feature effects in machine learning models that overcomes limitations of existing ALE methods, especially in high-dimensional and small-sample scenarios.

Contribution

The paper proposes Differential Accumulated Local Effects (DALE), a new ALE approximation that is computationally efficient, unbiased, and robust to out-of-distribution sampling, applicable to differentiable models.

Findings

DALE significantly reduces computational overhead.

DALE provides unbiased feature effect estimates under certain conditions.

Experiments show DALE's effectiveness on synthetic and real datasets.

Abstract

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.