Contrastive Explanations with Local Foil Trees

TL;DR

This paper introduces a method using local foil trees to generate contrastive explanations in high-dimensional ML, focusing on features that distinguish specific outputs from alternatives.

Contribution

It presents a novel approach leveraging local decision trees to produce contrastive explanations, reducing feature complexity in high-dimensional spaces.

Findings

Effective in identifying key features for contrastive explanations

Applicable to multiple benchmark classification tasks

Enhances interpretability in high-dimensional settings

Abstract

Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.