| Title: |
Counterfactual Explanations for Dynamic Multi-Valued Logic |
| Authors: |
Ribeiro, Tony; Folschette, Maxime; Magnin, Morgan; Inoue, Katsumi; Okazaki, Kotaro; Lo, Kuo-Yen; Nguyen, Tuan; Poschmann, Jeremie; Roquilly, Antoine |
| Contributors: |
Méthodes Formelles pour la Bioinformatique (LS2N - équipe MéForBio); Laboratoire des Sciences du Numérique de Nantes (LS2N); Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique); Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-NANTES UNIVERSITÉ - École Centrale de Nantes (Nantes Univ - ECN); Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST); Nantes Université - pôle Sciences et technologie; Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie; Nantes Université (Nantes Univ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique); Nantes Université (Nantes Univ); National Institute of Informatics (NII); Chercheur indépendant; NANTES UNIVERSITÉ - École Centrale de Nantes (Nantes Univ - ECN); BioComputing; Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL); Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS); Steelous Protocol; University of Science and Technology of Hanoi (USTH); Centre de Recherche en Transplantation et Immunologie - Center for Research in Transplantation and Translational Immunology (U1064 Inserm - CR2TI); Institut National de la Santé et de la Recherche Médicale (INSERM)-Nantes Université - UFR de Médecine et des Techniques Médicales (Nantes Univ - UFR MEDECINE); Nantes Université - pôle Santé; Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Santé; Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ); Nantes Université, CHU Nantes, INSERM, Anesthesie Réanimation, F-44000 Nantes, France; European Project |
| Source: |
Special Interest Group on Fundamental Problems in Artificial Intelligence 2025 (SIG-FPAI) ; https://hal.science/hal-05230575 ; Special Interest Group on Fundamental Problems in Artificial Intelligence 2025 (SIG-FPAI), Aug 2025, Toyama, Japan |
| Publisher Information: |
CCSD |
| Publication Year: |
2025 |
| Collection: |
Université de Nantes: HAL-UNIV-NANTES |
| Subject Terms: |
counterfactual explanations; dynamic systems; logical modeling; inductive logic programming; Explainable artificial intelligence; [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| Subject Geographic: |
Toyama; Japan |
| Description: |
International audience ; Counterfactual explanations are instrumental in helping humans gain insight into the decision-making processes of artificial intelligence systems by illustrating the effects of altering specific input variables. By presenting hypothetical scenarios, they foster transparency in artificial intelligence, enabling us to comprehend its operations more deeply and cultivate confidence in its dependability. This transparency is essential for the development of ethical artificial intelligence systems that are both equitable and accountable. In this paper, we expand upon the Learning From Interpretation Transition framework by proposing a theoretical modeling of counterfactual explanations for dynamic multi-valued logic programs. Furthermore, we introduce an efficient algorithm called CELOS that leverages properties over logic rules to compute all minimal counterfactual explanations. We show through theoretical results the correctness of our approaches. Practical evaluation is performed on benchmarks from biological literature and synthetic instances. |
| Document Type: |
conference object |
| Language: |
English |
| Availability: |
https://hal.science/hal-05230575; https://hal.science/hal-05230575v1/document; https://hal.science/hal-05230575v1/file/2025_07_26_SIG_FPAI.pdf |
| Rights: |
info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.1B16CF22 |
| Database: |
BASE |