On Relating 'Why?' and 'Why Not?' Explanations

12/21/2020
by   Alexey Ignatiev, et al.
0

Explanations of Machine Learning (ML) models often address a 'Why?' question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a 'Why Not?' question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between 'Why?' and 'Why Not?' explanations. Concretely, the paper proves that, for any given instance, 'Why?' explanations are minimal hitting sets of 'Why Not?' explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.

READ FULL TEXT

page 9

page 18

research
07/04/2019

On Validating, Repairing and Refining Heuristic ML Explanations

Recent years have witnessed a fast-growing interest in computing explana...
research
10/15/2021

Tree-based local explanations of machine learning model predictions, AraucanaXAI

Increasingly complex learning methods such as boosting, bagging and deep...
research
06/27/2023

Delivering Inflated Explanations

In the quest for Explainable Artificial Intelligence (XAI) one of the qu...
research
03/16/2023

Finding Minimum-Cost Explanations for Predictions made by Tree Ensembles

The ability to explain why a machine learning model arrives at a particu...
research
05/21/2021

Probabilistic Sufficient Explanations

Understanding the behavior of learned classifiers is an important task, ...
research
10/27/2022

Feature Necessity Relevancy in ML Classifier Explanations

Given a machine learning (ML) model and a prediction, explanations can b...
research
09/23/2020

The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets

For neural models to garner widespread public trust and ensure fairness,...

Please sign up or login with your details

Forgot password? Click here to reset