Explaining Predictive Uncertainty with Information Theoretic Shapley Values

by   David S. Watson, et al.
King's College London

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the 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 an efficient algorithm that performs 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.


page 1

page 2

page 3

page 4


Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

The mutual information between predictions and model parameters – also r...

An Information-Theoretic Framework for Unifying Active Learning Problems

This paper presents an information-theoretic framework for unifying acti...

Predictive and Causal Implications of using Shapley Value for Model Interpretation

Shapley value is a concept from game theory. Recently, it has been used ...

Explaining Models by Propagating Shapley Values of Local Components

In healthcare, making the best possible predictions with complex models ...

Prediction-Oriented Bayesian Active Learning

Information-theoretic approaches to active learning have traditionally f...

The Value of Interaction in Data Intelligence

In human computer interaction (HCI), it is common to evaluate the value ...

Please sign up or login with your details

Forgot password? Click here to reset