Results 1 to 10 of about 2,644 (209)

Shapley Values for Feature Selection: The Good, the Bad, and the Axioms

open access: yesIEEE Access, 2021
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for attribution in transferable utility games.
Daniel Vidali Fryer   +2 more
exaly   +3 more sources

Model independent feature attributions: Shapley values that uncover non-linear dependencies [PDF]

open access: yesPeerJ Computer Science, 2021
Shapley values have become increasingly popular in the machine learning literature, thanks to their attractive axiomatisation, flexibility, and uniqueness in satisfying certain notions of ‘fairness’. The flexibility arises from the myriad potential forms
Daniel Vidali Fryer   +2 more
doaj   +2 more sources

Computing Shapley Values in the Plane [PDF]

open access: yesDiscrete & Computational Geometry, 2022
new set of authors; several improvements with respect to v1; 31 pages; 21 ...
Sergio Cabello, Timothy M. Chan
openaire   +4 more sources

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

open access: yesBrain Sciences, 2022
Normal aging is associated with changes in volumetric indices of brain atrophy. A quantitative understanding of age-related brain changes can shed light on successful aging.
Jaime Gómez-Ramírez   +2 more
doaj   +1 more source

VMD-WSLSTM Load Prediction Model Based on Shapley Values

open access: yesEnergies, 2022
Accurate short-term load forecasting can ensure the safe operation of the grid. Decomposing load data into smooth components by decomposition algorithms is a common approach to address data volatility. However, each component of the decomposition must be
Bilin Shao, Yichuan Yan, Huibin Zeng
doaj   +1 more source

GPUTreeShap: massively parallel exact calculation of SHAP scores for tree ensembles [PDF]

open access: yesPeerJ Computer Science, 2022
SHapley Additive exPlanation (SHAP) values (Lundberg & Lee, 2017) provide a game theoretic interpretation of the predictions of machine learning models based on Shapley values (Shapley, 1953).
Rory Mitchell   +2 more
doaj   +2 more sources

Shapley Values as a Strategy for Ensemble Weights Estimation

open access: yesApplied Sciences, 2023
This study introduces a novel performance-based weighting scheme for ensemble learning using the Shapley value. The weighting uses the reciprocal of binary cross-entropy as a base learner’s performance metric and estimates its Shapley value to measure ...
Vaidotas Drungilas   +3 more
doaj   +1 more source

Explaining multivariate molecular diagnostic tests via Shapley values

open access: yesBMC Medical Informatics and Decision Making, 2021
Background Machine learning (ML) can be an effective tool to extract information from attribute-rich molecular datasets for the generation of molecular diagnostic tests.
Joanna Roder   +3 more
doaj   +1 more source

On weighted Shapley values [PDF]

open access: yesInternational Journal of Game Theory, 1987
Nonsymmetric Shapley values for coalitional form games with transferable utility are studied. The nonsymmetries are modeled through nonsymmetric weight systems defined on the players of the games. It is shown axiomatically that two families of solutions of this type are possible.
Ehud Kalai, Dov Samet
openaire   +3 more sources

Some Properties of Interval Shapley Values: An Axiomatic Analysis

open access: yesGames, 2023
Interval games are an extension of cooperative coalitional games, in which players are assumed to face payoff uncertainty. Characteristic functions thus assign a closed interval instead of a real number.
Shinichi Ishihara, Junnosuke Shino
doaj   +1 more source

Home - About - Disclaimer - Privacy