Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511661" target="_blank" >RIV/00216208:11320/25:10511661 - isvavai.cz</a>

Result on the web

<a href="https://dl.acm.org/doi/10.1145/3690624.3709300" target="_blank" >https://dl.acm.org/doi/10.1145/3690624.3709300</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3690624.3709300" target="_blank" >10.1145/3690624.3709300</a>

Result language

angličtina

Original language name

Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change

Original language description

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model changes, potentially invalidating previously generated CFEs and rendering user-induced input changes ineffective. Current methods addressing this issue often support only specific models or change types, require extensive hyperparameter tuning, or fail to provide probabilistic guarantees on CFE robustness to model changes. This paper proposes a novel approach for generating CFEs that provides probabilistic guarantees for any model and change type, while offering interpretable and easy-to-select hyperparameters. We establish a theoretical framework for probabilistically defining robustness to model change and demonstrate how our BetaRCE method directly stems from it. BetaRCE is a post-hoc method applied alongside a chosen base CFE generation method to enhance the qua

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

KDD &apos;25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

ISBN

979-8-4007-1245-6

ISSN

—

e-ISSN

—

Number of pages

12

Pages from-to

1277-1288

Publisher name

Association for Computing Machinery

Place of publication

New York, NY, USA

Event location

Toronto, Canada

Event date

Aug 3, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—