Model Agnostic Supervised Local Explanations

TL;DR

The paper introduces MAPLE, a highly accurate, model-agnostic interpretability system that combines local linear modeling with random forest insights to provide faithful explanations and global pattern detection.

Contribution

MAPLE is a novel model that offers accurate predictions and comprehensive interpretability, integrating local and global explanations without sacrificing accuracy.

Findings

MAPLE matches or exceeds random forest accuracy on UCI datasets.

MAPLE provides more faithful local explanations than LIME.

MAPLE detects global patterns and limitations in explanations.

Abstract

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in interpretability is designing explanation systems that can capture aspects of each of these explanation types, in order to develop a more thorough understanding of the model. We address this challenge in a novel model called MAPLE that uses local linear modeling techniques along with a dual interpretation of random forests (both as a supervised neighborhood approach and as a feature selection method). MAPLE has two fundamental advantages over existing interpretability systems. First, while it is effective as a black-box explanation system, MAPLE itself is a highly accurate predictive model that provides faithful self explanations, and thus sidesteps the typical accuracy-interpretability trade-off. Specifically, we demonstrate, on several UCI datasets, that MAPLE is at least as accurate as random forests and that it produces more faithful local explanations than LIME, a popular interpretability system. Second, MAPLE provides both example-based and local explanations and can detect global patterns, which allows it to diagnose limitations in its local explanations.