On Shapley value for measuring importance of dependent inputs

2016/10/06 by Owen, Art B., Prieur, Clémentine · 6 citations
#FOS: Mathematics #Numerical Analysis (math.NA) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1610.02080

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.

Cited by

• Fourier Analysis on the Boolean Hypercube via Hoeffding Functional Decomposition
• On Using the Shapley Value for Anomaly Localization: A Statistical Investigation
• ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
• GRASP-PsONet: Gradient-based Removal of Spurious Patterns for PsOriasis Severity Classification
• Effect Decomposition of Functional-Output Computer Experiments via Orthogonal Additive Gaussian Processes
• A Review and Comparison of Different Sensitivity Analysis Techniques in Practice

Related

• Explaining black box decisions by Shapley cohort refinement
• SHAFF: Fast and consistent SHApley eFfect estimates via random Forests
• Feature Importance: A Closer Look at Shapley Values and LOCO
• Shapley effects for sensitivity analysis with correlated inputs: comparisons with Sobol' indices, numerical estimation and applications
• Predictive and Causal Implications of using Shapley Value for Model\n Interpretation