Explaining Predictive Uncertainty with Information Theoretic Shapley Values

Autor:	Watson, David S., O'Hara, Joshua, Tax, Niek, Mudd, Richard, Guy, Ido
Rok vydání:	2023
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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 model outputs has received relatively little attention. We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs. We consider games with modified characteristic functions and find deep connections between the resulting Shapley values and fundamental quantities from information theory and conditional independence testing. We outline inference procedures for finite sample error rate control with provable guarantees, and implement efficient algorithms that perform well in a range of experiments on real and simulated data. Our method has applications to covariate shift detection, active learning, feature selection, and active feature-value acquisition. Comment: Camera ready version (NeurIPS 2023)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.05724 Zobrazit plný text záznamu View this record from Arxiv