Finding counterfactual explanations through constraint relaxations

Simple item page
dc.contributor.authorDev Gupta, Sharmi
dc.contributor.authorGenç, Begüm
dc.contributor.authorO'Sullivan, Barry
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.contributor.funderHorizon 2020en
dc.date.accessioned2023-01-11T16:28:39Z
dc.date.available2023-01-11T16:28:39Z
dc.date.issued2022-02
dc.date.updated2023-01-11T16:16:06Z
dc.description.abstractInteractive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility 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 out some of their constraints, there exists a solution". However, one can criticise this form of explanation as not being 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 which changes can be applied to their existing constraints rather than removing them. This approach has been extensively studied in the machine learning field, but requires a more thorough investigation in the context of constraint satisfaction. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation.en
dc.description.sponsorshipScience Foundation Ireland (SFI Grant 16/RC/3918; 12/RC/2289-P2; 18/CRT/6223, co-funded under the European Regional Development Fund); European Commission (TAILOR, HumanE AI Network, BRAINE, and StairwAI projects funded by EU Horizon 2020 under Grant Agreements 952215, 952026, 876967, and 101017142)en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationDev Gupta, S., Genc, B. and O'Sullivan, B. (2022) 'Finding counterfactual explanations through constraint relaxations', AAA1 22 - Thirty-Sixth AAAI Conference on Artificial Intelligence: Explainable Agency in Artificial Intelligence Workshop (EAAI'22), Online, 22 Feb - 01 Mar.en
dc.identifier.endpage9en
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/14044
dc.language.isoenen
dc.publisherAAAIen
dc.relation.ispartofAAA1 22 - Thirty-Sixth AAAI Conference on Artificial Intelligence
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/952215/EU/Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization/TAILORen
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/952026/EU/HumanE AI Network/HumanE-AI-Neten
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::ECSEL-RIA/876967/EU/Big data pRocessing and Artificial Intelligence at the Network Edge/BRAINEen
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::IA/101017142/EU/Stairway to AI: Ease the Engagement of Low-Tech users to the AI-on-Demand platform through AI/StairwAIen
dc.relation.urihttps://sites.google.com/view/eaai-ws-2022/topic
dc.subjectCounterfactual explanationen
dc.subjectMaximal relaxationen
dc.subjectConstraint programmingen
dc.titleFinding counterfactual explanations through constraint relaxationsen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Finding_Counterfactual_Explanations_through_Constraint_Relaxations_CP2022.pdf
Size:
567.32 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
Computer Science - Conference Items
Insight Centre for Data Analytics - Conference Items