Saved in:
Bibliographic Details
Main Authors: Hamer, Jenny, Perello, Nicholas, Valladares, Jake, Viswanathan, Vignesh, Zick, Yair
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.15557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929589070069760
author Hamer, Jenny
Perello, Nicholas
Valladares, Jake
Viswanathan, Vignesh
Zick, Yair
author_facet Hamer, Jenny
Perello, Nicholas
Valladares, Jake
Viswanathan, Vignesh
Zick, Yair
contents Algorithmic recourse is a process that leverages counterfactual explanations, going beyond understanding why a system produced a given classification, to providing a user with actions they can take to change their predicted outcome. Existing approaches to compute such interventions -- known as recourse -- identify a set of points that satisfy some desiderata -- e.g. an intervention in the underlying causal graph, minimizing a cost function, etc. Satisfying these criteria, however, requires extensive knowledge of the underlying model structure, an often unrealistic amount of information in several domains. We propose a data-driven and model-agnostic framework to compute counterfactual explanations. We introduce StEP, a computationally efficient method that offers incremental steps along the data manifold that directs users towards their desired outcome. We show that StEP uniquely satisfies a desirable set of axioms. Furthermore, via a thorough empirical and theoretical investigation, we show that StEP offers provable robustness and privacy guarantees while outperforming popular methods along important metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2306_15557
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Simple Steps to Success: A Method for Step-Based Counterfactual Explanations
Hamer, Jenny
Perello, Nicholas
Valladares, Jake
Viswanathan, Vignesh
Zick, Yair
Machine Learning
Algorithmic recourse is a process that leverages counterfactual explanations, going beyond understanding why a system produced a given classification, to providing a user with actions they can take to change their predicted outcome. Existing approaches to compute such interventions -- known as recourse -- identify a set of points that satisfy some desiderata -- e.g. an intervention in the underlying causal graph, minimizing a cost function, etc. Satisfying these criteria, however, requires extensive knowledge of the underlying model structure, an often unrealistic amount of information in several domains. We propose a data-driven and model-agnostic framework to compute counterfactual explanations. We introduce StEP, a computationally efficient method that offers incremental steps along the data manifold that directs users towards their desired outcome. We show that StEP uniquely satisfies a desirable set of axioms. Furthermore, via a thorough empirical and theoretical investigation, we show that StEP offers provable robustness and privacy guarantees while outperforming popular methods along important metrics.
title Simple Steps to Success: A Method for Step-Based Counterfactual Explanations
topic Machine Learning
url https://arxiv.org/abs/2306.15557