Generally-Occurring Model Change for Robust Counterfactual Explanations

TL;DR

This paper introduces a generalized concept of model change called Generally-Occurring Model Change, enhancing robustness analysis of counterfactual explanations under various model parameter variations and dataset perturbations.

Contribution

It extends the existing concept of Naturally-Occurring Model Change to a broader, more applicable framework and provides theoretical guarantees for robustness in counterfactual explanations.

Findings

Proposes the concept of Generally-Occurring Model Change with probabilistic guarantees.

Analyzes robustness of counterfactual explanations under model and data perturbations.

Provides theoretical results combining optimization theory and model change analysis.

Abstract

With the increasing impact of algorithmic decision-making on human lives, the interpretability of models has become a critical issue in machine learning. Counterfactual explanation is an important method in the field of interpretable machine learning, which can not only help users understand why machine learning models make specific decisions, but also help users understand how to change these decisions. Naturally, it is an important task to study the robustness of counterfactual explanation generation algorithms to model changes. Previous literature has proposed the concept of Naturally-Occurring Model Change, which has given us a deeper understanding of robustness to model change. In this paper, we first further generalize the concept of Naturally-Occurring Model Change, proposing a more general concept of model parameter changes, Generally-Occurring Model Change, which has a wider range of applicability. We also prove the corresponding probabilistic guarantees. In addition, we consider a more specific problem, data set perturbation, and give relevant theoretical results by combining optimization theory.