Counterfactual explanation through constraint relaxation

Simple item page
dc.contributor.authorGupta, Sharmi Deven
dc.contributor.authorO'Sullivan, Barryen
dc.contributor.authorQuesada, Luisen
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2025-04-16T15:13:51Z
dc.date.available2025-04-16T15:13:51Z
dc.date.issued2025-01-28en
dc.description.abstractInteractive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover feasibility is to eliminate the constraints that cause the conflicts in the system. This approach allows the system to provide an explanation as: “if the user is willing to drop some of their constraints, there exists a solution”. However, this form of explanation might not be very informative. A counterfactual explanation is a type of explanation that can provide a basis for the user to recover feasibility by helping them understand what changes can be applied to their existing constraints rather than removing them. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation. We have evaluated our approach using well known instances that occur in industrial applications and demonstrated the relevance of multi-point relaxations.en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationGupta, S.D., O’Sullivan, B. and Quesada, L. (2024) ‘Counterfactual explanation through constraint relaxation’, 2024 IEEE 36th International Conference on Tools with Artificial Intelligence (ICTAI), Herndon, VA, USA, 28-30 October ,pp. 396–403. 2024 .Available at: https://doi.org/10.1109/ICTAI62512.2024.00064en
dc.identifier.doi10.1109/ICTAI62512.2024.00064en
dc.identifier.eissn2375-0197en
dc.identifier.endpage403en
dc.identifier.issn1082-3409en
dc.identifier.startpage396en
dc.identifier.urihttps://hdl.handle.net/10468/17279
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/Centres for Research Training (CRT) Programme/18/CRT/6223/IE/SFI Centre for Research Training in Artificial Intelligence/en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/Research Centres Programme::Phase 2/12/RC/2289_P2/IE/INSIGHT_Phase 2 /en
dc.relation.urihttps://ieeexplore.ieee.org/xpl/conhome/10849351/proceedingen
dc.rights© 2025, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectCounterfactual explanationen
dc.subjectMaximal relaxationen
dc.subjectConstraint programmingen
dc.titleCounterfactual explanation through constraint relaxationen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ICTAI2024_AAV.pdf
Size:
517.81 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Insight Centre for Data Analytics - Conference Items
Computer Science - Conference Items