Counterfactuals in fuzzy relational models

Basit Öğe Kaydı
dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorAl-Hmouz, Rami
dc.contributor.authorPedrycz, Witold
dc.contributor.authorAmmari, Ahmed
dc.date.accessioned2025-05-09T06:52:15Z
dc.date.available2025-05-09T06:52:15Z
dc.date.issued2024
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü
dc.description.abstractGiven the pressing need for explainability in Machine Learning systems, the studies on counterfactual explanations have gained significant interest. This research delves into this timely problem cast in a unique context of relational systems described by fuzzy relational equations. We develop a comprehensive solution to the counterfactual problems encountered in this setting, which is a novel contribution to the field. An underlying optimization problem is formulated, and its gradient-based solution is constructed. We demonstrate that the non-uniqueness of the derived solution is conveniently formalized and quantified by admitting a result coming in the form of information granules of a higher type, namely type-2 or interval-valued fuzzy set. The construction of the solution in this format is realized by invoking the principle of justifiable granularity, another innovative aspect of our research. We also discuss ways of designing fuzzy relations and elaborate on methods of carrying out counterfactual explanations in rule-based models. Illustrative examples are included to present the performance of the method and interpret the obtained results. © The Author(s) 2024.
dc.description.sponsorshipThis project was funded by Sultan Qaboos University, Sultanateof Oman. The authors, therefore, acknowledge with thanksthe technical and financial support.
dc.identifier.citationAl-Hmouz, R., Pedrycz, W., & Ammari, A. (2024). Counterfactuals in fuzzy relational models. Artificial Intelligence Review, 57(12), 1-19.
dc.identifier.doi10.1007/s10462-024-10996-9
dc.identifier.issn02692821
dc.identifier.issue12
dc.identifier.scopusqualityQ1
dc.identifier.urihttp://dx.doi.org/10.1007/s10462-024-10996-9
dc.identifier.urihttps://hdl.handle.net/20.500.12713/7243
dc.identifier.volume57
dc.identifier.wosWOS:001338463600001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherSpringer Nature
dc.relation.ispartofArtificial Intelligence Review
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectCounterfactual Explanation
dc.subjectExplainability
dc.subjectFuzzy Relational Equations
dc.subjectPrinciple of Justifiable Granularity
dc.subjectType-2 Fuzzy Sets
dc.titleCounterfactuals in fuzzy relational models
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Counterfactuals-in-fuzzy-relational-modelsArtificial-Intelligence-Review.pdf
Boyut:
3.22 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Elektrik-Elektronik Mühendisliği Bölümü Makale Koleksiyonu