paper-with-me

홈 › Papers

Statistical Aspects of SHAP: Functional ANOVA for Model Interpretation

2022-08-21 · Andrew Herren, P. Richard Hahn

SHAP is a popular method for measuring variable importance in machine learning models. In this paper, we study the algorithm used to estimate SHAP scores and outline its connection to the functional ANOVA decomposition. We use this connection to show that challenges in SHAP approximations largely relate to the choice of a feature distribution and the number of $2^p$ ANOVA terms estimated. We argue that the connection between machine learning explainability and sensitivity analysis is illuminating in this case, but the immediate practical consequences are not obvious since the two fields face a different set of constraints. Machine learning explainability concerns models which are inexpensive to evaluate but often have hundreds, if not thousands, of features. Sensitivity analysis typically deals with models from physics or engineering which may be very time consuming to run, but operate on a comparatively small space of inputs.

📄 PDF Abstract BibTeX arXiv:2208.09970

Code (1)

andrewherren/shap-anova-examples 공식 구현

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

SHAP 설명 없음

Similar Papers 제목 키워드 기반

Tensor Product Neural Networks for Functional ANOVA Model

2025-02-21 · Seokhun Park, Insung Kong, Yongchan Choi, Chanmoo Park 외

Interpretability for machine learning models is becoming more and more important as machine learning models become more complex. The functional ANOVA model, which decomposes a high-dimensional function into a sum of lowe…

model

META-ANOVA: Screening interactions for interpretable machine learning

2024-08-02 · Yongchan Choi, Seokhun Park, Chanmoo Park, Dongha Kim 외

There are two things to be considered when we evaluate predictive models. One is prediction accuracy,and the other is interpretability. Over the recent decades, many prediction models of high performance, such as ensembl…

Interpretable Machine LearningPrediction

Exact Functional ANOVA Decomposition for Categorical Inputs Models

2026-03-03 · Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa, Jean-Michel Loubes 외 arxiv

Functional ANOVA offers a principled framework for interpretability by decomposing a model's prediction into main effects and higher-order interactions. For independent features, this decomposition is well-defined, stron…

Bayesian Additive Regression Trees for functional ANOVA model

2025-09-03 · Seokhun Park, Insung Kong, Yongdai Kim arxiv

Bayesian Additive Regression Trees (BART) is a powerful statistical model that leverages the strengths of Bayesian inference and regression trees. It has received significant attention for capturing complex non-linear re…

Bayesian Inference

A Bayesian explanation of machine learning models based on modes and functional ANOVA

2024-11-05 · Quan Long

Most methods in explainable AI (XAI) focus on providing reasons for the prediction of a given set of features. However, we solve an inverse explanation problem, i.e., given the deviation of a label, find the reasons of t…