RbX: Region-based explanations of prediction models

10/17/2022
by   Ismael Lemhadri, et al.
0

We introduce region-based explanations (RbX), a novel, model-agnostic method to generate local explanations of scalar outputs from a black-box prediction model using only query access. RbX is based on a greedy algorithm for building a convex polytope that approximates a region of feature space where model predictions are close to the prediction at some target point. This region is fully specified by the user on the scale of the predictions, rather than on the scale of the features. The geometry of this polytope - specifically the change in each coordinate necessary to escape the polytope - quantifies the local sensitivity of the predictions to each of the features. These "escape distances" can then be standardized to rank the features by local importance. RbX is guaranteed to satisfy a "sparsity axiom," which requires that features which do not enter into the prediction model are assigned zero importance. At the same time, real data examples and synthetic experiments show how RbX can more readily detect all locally relevant features than existing methods.

READ FULL TEXT
research
10/29/2019

bLIMEy: Surrogate Prediction Explanations Beyond LIME

Surrogate explainers of black-box machine learning predictions are of pa...
research
07/02/2018

Logical Explanations for Deep Relational Machines Using Relevance Information

Our interest in this paper is in the construction of symbolic explanatio...
research
02/15/2023

Streamlining models with explanations in the learning loop

Several explainable AI methods allow a Machine Learning user to get insi...
research
02/24/2021

Practitioners' Perceptions of the Goals and Visual Explanations of Defect Prediction Models

Software defect prediction models are classifiers that are constructed f...
research
06/24/2022

Analyzing the Effects of Classifier Lipschitzness on Explainers

Machine learning methods are getting increasingly better at making predi...
research
10/27/2020

A robust low data solution: dimension prediction of semiconductor nanorods

Precise control over dimension of nanocrystals is critical to tune the p...
research
10/28/2021

Explaining Latent Representations with a Corpus of Examples

Modern machine learning models are complicated. Most of them rely on con...

Please sign up or login with your details

Forgot password? Click here to reset