DeepAI AI Chat
Log In Sign Up

Interpretable Counterfactual Explanations Guided by Prototypes

07/03/2019
by   Arnaud Van Looveren, et al.
Seldon
1

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and result in more interpretable explanations. We introduce two novel metrics to quantitatively evaluate local interpretability at the instance level. We use these metrics to illustrate the effectiveness of our method on an image and tabular dataset, respectively MNIST and Breast Cancer Wisconsin (Diagnostic). The method also eliminates the computational bottleneck that arises because of numerical gradient evaluation for black box models.

READ FULL TEXT

page 1

page 3

page 6

page 10

page 12

page 13

11/17/2022

Features Compression based on Counterfactual Analysis

Counterfactual Explanations are becoming a de-facto standard in post-hoc...
12/04/2019

Counterfactual Explanation Algorithms for Behavioral and Textual Data

We study the interpretability of predictive systems that use high-dimens...
12/02/2021

Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis

Earnings call (EC), as a periodic teleconference of a publicly-traded co...
02/28/2021

Model-Agnostic Explainability for Visual Search

What makes two images similar? We propose new approaches to generate mod...
07/04/2019

Explaining Predictions from Tree-based Boosting Ensembles

Understanding how "black-box" models arrive at their predictions has spa...
11/03/2020

MAIRE – A Model-Agnostic Interpretable Rule Extraction Procedure for Explaining Classifiers

The paper introduces a novel framework for extracting model-agnostic hum...