DeepAI AI Chat
Log In Sign Up

Scaling Guarantees for Nearest Counterfactual Explanations

by   Kiarash Mohammadi, et al.

Counterfactual explanations (CFE) are being widely used to explain algorithmic decisions, especially in consequential decision-making contexts (e.g., loan approval or pretrial bail). In this context, CFEs aim to provide individuals affected by an algorithmic decision with the most similar individual (i.e., nearest individual) with a different outcome. However, while an increasing number of works propose algorithms to compute CFEs, such approaches either lack in optimality of distance (i.e., they do not return the nearest individual) and perfect coverage (i.e., they do not provide a CFE for all individuals); or they cannot handle complex models, such as neural networks. In this work, we provide a framework based on Mixed-Integer Programming (MIP) to compute nearest counterfactual explanations with provable guarantees and with runtimes comparable to gradient-based approaches. Our experiments on the Adult, COMPAS, and Credit datasets show that, in contrast with previous methods, our approach allows for efficiently computing diverse CFEs with both distance guarantees and perfect coverage.


page 1

page 2

page 3

page 4


Algorithmic Recourse: from Counterfactual Explanations to Interventions

As machine learning is increasingly used to inform consequential decisio...

Model-Agnostic Counterfactual Explanations for Consequential Decisions

Predictive models are being increasingly used to support consequential d...

Efficient Search for Diverse Coherent Explanations

This paper proposes new search algorithms for counterfactual explanation...

Endogenous Macrodynamics in Algorithmic Recourse

Existing work on Counterfactual Explanations (CE) and Algorithmic Recour...

Optimal Counterfactual Explanations in Tree Ensembles

Counterfactual explanations are usually generated through heuristics tha...

Decisions, Counterfactual Explanations and Strategic Behavior

Data-driven predictive models are increasingly used to inform decisions ...

Bayesian Hierarchical Models for Counterfactual Estimation

Counterfactual explanations utilize feature perturbations to analyze the...