Scaling Guarantees for Nearest Counterfactual Explanations

TL;DR

This paper introduces a Mixed-Integer Programming framework for computing nearest counterfactual explanations with guarantees on optimality and coverage, efficiently handling complex models like neural networks.

Contribution

It presents a novel MIP-based method that provides provable guarantees for nearest counterfactual explanations, outperforming existing approaches in coverage and optimality.

Findings

Efficiently computes diverse CFEs with distance guarantees.

Achieves perfect coverage for all individuals in datasets.

Handles complex models such as neural networks effectively.

Abstract

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.