Finding Counterfactual Explanations through Constraint Relaxations

04/07/2022
by   Sharmi Dev Gupta, et al.
0

Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This approach allows the system to provide an explanation as: "if the user is willing to drop out some of their constraints, there exists a solution". However, one can criticise this form of explanation as not being very informative. A counterfactual explanation is a type of explanation that can provide a basis for the user to recover feasibility by helping them understand which changes can be applied to their existing constraints rather than removing them. This approach has been extensively studied in the machine learning field, but requires a more thorough investigation in the context of constraint satisfaction. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/12/2022

Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints

We present a human-in-the-loop approach to generate counterfactual (CF) ...
research
06/11/2020

A framework for step-wise explaining how to solve constraint satisfaction problems

We explore the problem of step-wise explaining how to solve constraint s...
research
01/25/2023

Counterfactual Editing for Search Result Explanation

Recently substantial improvements in neural retrieval methods also bring...
research
06/25/2019

Explaining Deep Learning Models with Constrained Adversarial Examples

Machine learning algorithms generally suffer from a problem of explainab...
research
05/25/2021

Efficiently Explaining CSPs with Unsatisfiable Subset Optimization

We build on a recently proposed method for explaining solutions of const...
research
03/26/2023

CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows

Counterfactual explanation is a form of interpretable machine learning t...
research
01/26/2023

Finding Regions of Counterfactual Explanations via Robust Optimization

Counterfactual explanations play an important role in detecting bias and...

Please sign up or login with your details

Forgot password? Click here to reset