Explainability is NOT a Game
In: https://hal.science/hal-04154767 ; 2023, 2023
Online
report
Zugriff:
Publication prévue lors d'une conférence de l'Association for Computing Machinery (ACM) ; Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding complex machine learning (ML) models. One of the hallmarks of XAI are measures of relative feature importance, which are theoretically justified through the use of Shapley values. This paper builds on recent work and offers a simple argument for why Shapley values can provide misleading measures of relative feature importance, by assigning more importance to features that are irrelevant for a prediction, and assigning less importance to features that are relevant for a prediction. The significance of these results is that they effectively challenge the many proposed uses of measures of relative feature importance in a fast-growing range of high-stakes application domains. CCS Concepts • Computing methodologies → Artificial intelligence; Machine learning algorithms; Machine learning; • Theory of computation → Automated reasoning.
Titel: |
Explainability is NOT a Game
|
---|---|
Autor/in / Beteiligte Person: | Marques-Silva, Joao ; Huang, Xuanxiang ; Argumentation, Décision, Raisonnement, Incertitude et Apprentissage (IRIT-ADRIA) ; Institut de recherche en informatique de Toulouse (IRIT) ; Université Toulouse Capitole (UT Capitole) ; Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J) ; Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3) ; Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP) ; Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI) ; Université Toulouse - Jean Jaurès (UT2J) ; Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3) ; Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole) ; Université de Toulouse (UT) ; Centre National de la Recherche Scientifique (CNRS) ; Université Toulouse III - Paul Sabatier (UT3) ; ANR-19-PI3A-0004,Future - PI3A ; European Project: H2020 - ICT38,COALA |
Link: | |
Zeitschrift: | https://hal.science/hal-04154767 ; 2023, 2023 |
Veröffentlichung: | HAL CCSD, 2023 |
Medientyp: | report |
Schlagwort: |
|
Sonstiges: |
|