paper-with-me

홈 › Papers

Shapley Values with Uncertain Value Functions

2023-01-19 · Raoul Heese, Sascha Mücke, Matthias Jakobs, Thore Gerlach, Nico Piatkowski

We propose a novel definition of Shapley values with uncertain value functions based on first principles using probability theory. Such uncertain value functions can arise in the context of explainable machine learning as a result of non-deterministic algorithms. We show that random effects can in fact be absorbed into a Shapley value with a noiseless but shifted value function. Hence, Shapley values with uncertain value functions can be used in analogy to regular Shapley values. However, their reliable evaluation typically requires more computational effort.

📄 PDF Abstract BibTeX arXiv:2301.08086

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Explaining Predictive Uncertainty with Information Theoretic Shapley Values

2023-09-21 · NeurIPS 2023 11

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of…

Active LearningDecision Making Under UncertaintyDepth Aleatoric Uncertainty EstimationExplainable Artificial Intelligence (XAI)+1

Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals

2025-05-19 · Marouane Il Idrissi, Agathe Fernandes Machado, Ewen Gallic, Arthur Charpentier

Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, o…

AttributeConformal PredictionFeature ImportancePrediction Intervals

Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models

2023-05-24 · NeurIPS 2023 11

We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs. Our method is based on the popular solution concept of Shapley values extended…

Gaussian Processes

Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration

2024-03-07 · Julian Rodemann, Federico Croppi, Philipp Arens, Yusuf Sale 외

Bayesian optimization (BO) with Gaussian processes (GP) has become an indispensable algorithm for black box optimization problems. Not without a dash of irony, BO is often considered a black box itself, lacking ways to p…

Bayesian OptimizationGaussian Processes

A Refutation of Shapley Values for Explainability

2023-09-06 · Xuanxiang Huang, Joao Marques-Silva

Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was br…