DeepAI AI Chat
Log In Sign Up

The many Shapley values for model explanation

by   Mukund Sundararajan, et al.

The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The Shapley value [1] is known to be the unique method that satisfies certain desirable properties, and this motivates its use. Unfortunately, despite this uniqueness result, there are a multiplicity of Shapley values used in explaining a model's prediction. This is because there are many ways to apply the Shapley value that differ in how they reference the model, the training data, and the explanation context. In this paper, we study an approach that applies the Shapley value to conditional expectations (CES) of sets of features (cf. [2]) that subsumes several prior approaches within a common framework. We provide the first algorithm for the general version of CES. We show that CES can result in counterintuitive attributions in theory and in practice (we study a diabetes prediction task); for instance, CES can assign non-zero attributions to features that are not referenced by the model. In contrast, we show that an approach called the Baseline Shapley (BS) does not exhibit counterintuitive attributions; we support this claim with a uniqueness (axiomatic) result. We show that BS is a special case of CES, and CES with an independent feature distribution coincides with a randomized version of BS. Thus, BS fits into the CES framework, but does not suffer from many of CES's deficiencies.


page 1

page 2

page 3

page 4


The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory

Recently, a number of techniques have been proposed to explain a machine...

Explaining the Model and Feature Dependencies by Decomposition of the Shapley Value

Shapley values have become one of the go-to methods to explain complex m...

Joint Shapley values: a measure of joint feature importance

The Shapley value is one of the most widely used model-agnostic measures...

Explaining Preferences with Shapley Values

While preference modelling is becoming one of the pillars of machine lea...

Addendum to "Tilings problems on Baumslag-Solitar groups"

In our article in MCU'2013 we state the the Domino problem is undecidabl...

Explaining the data or explaining a model? Shapley values that uncover non-linear dependencies

Shapley values have become increasingly popular in the machine learning ...

Valid distribution-free inferential models for prediction

A fundamental problem in statistics and machine learning is that of usin...