Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Distributional Counterfactual Explanations With Optimal Transport

Title: Distributional Counterfactual Explanations With Optimal Transport
Authors: You, Lei; Cao, Lele; Nilsson, Mattias; Zhao, Bo; Lei, Lei
Contributors: Department of Computer Science; Computer Science Professors; Computer Science - Computing Systems (ComputingSystems) - Research area; Computer Science - Large-scale Computing and Data Analysis (LSCA) - Research area; Computer Science - Artificial Intelligence and Machine Learning (AIML) - Research area; Professorship Zhao Bo; Technical University of Denmark; Microsoft; Neko Health; Xi'an Jiaotong University; Aalto-yliopisto; Aalto University
Publication Year: 2025
Collection: Aalto University Publication Archive (Aaltodoc) / Aalto-yliopiston julkaisuarkistoa
Description: Counterfactual explanations (CE) are the de facto method for providing insights into black-box decision-making models by identifying alternative inputs that lead to different outcomes. However, existing CE approaches, including group and global methods, focus pre-dominantly on specific input modifications, lacking the ability to capture nuanced distributional characteristics that influence model outcomes across the entire input-output spectrum. This paper proposes distributional counterfactual explanation (DCE), shifting focus to the distributional properties of observed and counterfactual data, thus providing broader insights. DCE is particularly beneficial for stakeholders making strategic decisions based on statistical data analysis, as it makes the statistical distribution of the counterfactual resembles the one of the factual when aligning model outputs with a target distribution—something that the existing CE methods cannot fully achieve. We leverage optimal transport (OT) to formulate a chance-constrained optimization problem, deriving a counterfactual distribution aligned with its factual counterpart, supported by statistical confidence. The efficacy of this approach is demonstrated through experiments, highlighting its potential to provide deeper insights into decision-making models. ; Peer reviewed
Document Type: conference object
File Description: application/pdf
Language: English
Relation: International Conference on Artificial Intelligence and Statistics; Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS) 2025; pp. 1135-1143; Proceedings of Machine Learning Research; Volume 258; PURE LINK: https://proceedings.mlr.press/v258/you25a.html; PURE FILEURL: https://research.aalto.fi/files/190398677/Distributional_Counterfactual_Explanations_With_Optimal_Transport.pdf; https://aaltodoc.aalto.fi/handle/123456789/138921
Availability: https://aaltodoc.aalto.fi/handle/123456789/138921
Rights: openAccess ; CC BY ; https://creativecommons.org/licenses/by/4.0/
Accession Number: edsbas.B25B6B2A
Database: BASE