Model Agnostic Contrastive Explanations for Structured Data

TL;DR

This paper introduces MACEM, a model-agnostic method for generating contrastive explanations for any classification model using only class probability queries, applicable to structured data including real and categorical features.

Contribution

We propose MACEM, a novel, model-agnostic approach for contrastive explanations that handles real and categorical features, extending previous methods to a broader range of models and data types.

Findings

Effective on 5 public datasets across diverse domains

Generates meaningful contrastive explanations for various models

Handles real and categorical features explicitly

Abstract

Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for \emph{any} classification model where one is able to \emph{only} query the class probabilities for a desired input. This allows us to generate contrastive explanations for not only neural networks, but models such as random forests, boosted trees and even arbitrary ensembles that are still amongst the state-of-the-art when learning on structured data [13]. Moreover, to obtain meaningful explanations we propose a principled approach to handle real and categorical features leading to novel formulations for computing pertinent positives and negatives that form the essence of a contrastive explanation. A detailed treatment of the different data types of this nature was not performed in the previous work, which assumed all features to be positive real valued with zero being indicative of the least interesting value. We part with this strong implicit assumption and generalize these methods so as to be applicable across a much wider range of problem settings. We quantitatively and qualitatively validate our approach over 5 public datasets covering diverse domains.