Counterfactual Explanations for Optimization-Based Decisions in the Context of the GDPR

Anton Korikov, Alexander Shleyfman, J. Christopher Beck

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The General Data Protection Regulations (GDPR) entitle individuals to explanations for automated decisions. The form, comprehensibility, and even existence of such explanations remain open problems, investigated as part of explainable AI. We adopt the approach of counterfactual explanations and apply it to decisions made by declarative optimization models. We argue that inverse combinatorial optimization is particularly suited for counterfactual explanations but that the computational difficulties and relatively nascent literature make its application a challenge. To make progress, we address the case of counterfactual explanations that isolate the minimal differences for an individual. We show that under two common optimization functions, full inverse optimization is unnecessary. In particular, we show that for functions of the form of the sum of weighted binary variables, which includes frameworks such as weighted MaxSAT, a solution can be found by solving a slightly modified version of the original optimization model. In contrast, the sum of weighted integer variables can be solved with a binary search over a series of modifications to the original model.

Original languageEnglish
Title of host publicationProceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
EditorsZhi-Hua Zhou
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4097-4103
Number of pages7
ISBN (Electronic)9780999241196
StatePublished - 2021
Externally publishedYes
Event30th International Joint Conference on Artificial Intelligence, IJCAI 2021 - Virtual, Online, Canada
Duration: 19 Aug 202127 Aug 2021

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference30th International Joint Conference on Artificial Intelligence, IJCAI 2021
Country/TerritoryCanada
CityVirtual, Online
Period19/08/2127/08/21

Bibliographical note

Publisher Copyright:
© 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.

Fingerprint

Dive into the research topics of 'Counterfactual Explanations for Optimization-Based Decisions in the Context of the GDPR'. Together they form a unique fingerprint.

Cite this