On Shapley Value for Measuring Importance of Dependent Inputs
From MaRDI portal
Abstract: This paper makes the case for using Shapley value to quantify the importance of random input variables to a function. Alternatives based on the ANOVA decomposition can run into conceptual and computational problems when the input variables are dependent. Our main goal here is to show that Shapley value removes the conceptual problems. We do this with some simple examples where Shapley value leads to intuitively reasonable nearly closed form values.
Recommendations
- Estimation of high-order moment-independent importance measures for Shapley value analysis
- scientific article; zbMATH DE number 7566076
- On weighted Shapley values
- A new approach for evaluating the Shapely value
- scientific article; zbMATH DE number 4164591
- A new weight scheme for the Shapley value
- scientific article; zbMATH DE number 26541
- Computing Shapley effects for sensitivity analysis
- scientific article; zbMATH DE number 6139431
- A Shapley value representation of network potentials
Cites work
- Contributions to the theory of games. Vol. II
- Copulas for order statistics with prescribed margins
- Generalized Hoeffding-Sobol decomposition for dependent variables -- application to sensitivity analysis
- Generalized Sobol sensitivity indices for dependent variables: numerical methods
- scientific article; zbMATH DE number 3713012 (Why is no real title available?)
- scientific article; zbMATH DE number 1464593 (Why is no real title available?)
- scientific article; zbMATH DE number 777873 (Why is no real title available?)
- scientific article; zbMATH DE number 1425054 (Why is no real title available?)
- Morgenstern's bivariate distribution and its application to point processes
- On sensitivity estimation for nonlinear mathematical models
- Polynomial calculation of the Shapley value based on sampling
- Replication procedure for grouped Sobol' indices estimation in dependent uncertainty spaces
- Shapley Effects for Global Sensitivity Analysis: Theory and Computation
- Sobol' indices and Shapley value
- The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
- Variance allocation and Shapley value
- Variance components and generalized Sobol' indices
Cited in
(47)- Variance allocation and Shapley value
- Sensitivity indices for independent groups of variables
- Interpretable concept-based classification with Shapley values
- Assessment of the influence of features on a classification problem: an application to COVID-19 patients
- On Shapley value interpretability in concept-based learning with formal concept analysis
- Global sensitivity analysis in epidemiological modeling
- Is mortality or interest rate the most important risk in annuity models? A comparison of sensitivity analysis methods
- Data-driven inverse modelling through neural network (deep learning) and computational heat transfer
- Explaining predictive models using Shapley values and non-parametric vine copulas
- Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
- Sobol' indices and Shapley value
- Variance reduction for estimation of Shapley effects and adaptation to unknown input distribution
- Global sensitivity analysis for statistical model parameters
- Tensor algorithms for advanced sensitivity metrics
- Fair Attribution of Functional Contribution in Artificial and Biological Networks
- Shapley effects for sensitivity analysis with dependent inputs: bootstrap and kriging-based algorithms
- Efficient estimation of the ANOVA mean dimension, with an application to neural net classification
- Goal-oriented Shapley effects with special attention to the quantile-oriented case
- Block-diagonal covariance estimation and application to the Shapley effects in sensitivity analysis
- scientific article; zbMATH DE number 7566076 (Why is no real title available?)
- On the comparison of Shapley values for variance and standard deviation games
- Gaussian linear approximation for the estimation of the Shapley effects
- Computing Shapley effects for sensitivity analysis
- A Shapley-Owen index for interaction quantification
- A theory of dichotomous valuation with applications to variable selection
- Variance reduced Shapley value estimation for trustworthy data valuation
- Variable Selection Via Thompson Sampling
- Tail variance allocation, Shapley value, and the majorization problem
- Construction of rating systems using global sensitivity analysis: a numerical investigation
- Total effects with constrained features
- Efficient Shapley performance attribution for least-squares regression
- Proportional marginal effects for global sensitivity analysis
- A comparative study of methods for estimating model-agnostic Shapley value explanations
- Fast Approximation of the Shapley Values Based on Order-of-Addition Experimental Designs
- Feature importance: a closer look at Shapley values and LOCO
- Factor Importance Ranking and Selection Using Total Indices
- Variable importance measures for heterogeneous treatment effects
- Accelerating the computation of Shapley effects for datasets with many observations
- Shapley effects as a global sensitivity metric for robust design and control
- Shapley Curves: A Smoothing Perspective
- An Inference Method for Global Sensitivity Analysis
- A copula-based data augmentation strategy for the sensitivity analysis of extreme operational losses
- An Exact Game-Theoretic Variable Importance Index for Generalized Additive Models
- Contribution of subsets of variables in global sensitivity analysis with dependent variables
- The many Shapley values for explainable artificial intelligence: a sensitivity analysis perspective
- Sensitivity-based measures of discrimination in insurance pricing
- Estimation of high-order moment-independent importance measures for Shapley value analysis
This page was built for publication: On Shapley Value for Measuring Importance of Dependent Inputs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4636414)
