Simple Steps to Success: A Method for Step-Based Counterfactual Explanations

TL;DR

This paper introduces StEP, a data-driven, model-agnostic method for generating step-by-step counterfactual explanations that are efficient, robust, and privacy-preserving, aiding users in achieving desired outcomes.

Contribution

The paper presents StEP, a novel, computationally efficient framework for step-based counterfactual explanations that requires less knowledge of the underlying model and satisfies key axioms.

Findings

StEP outperforms existing methods on key metrics.

StEP provides provable robustness and privacy guarantees.

StEP offers incremental, data manifold-aligned steps for user guidance.

Abstract

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.