The Shapley Value of coalition of variables provides better explanations

03/24/2021
by   Salim I. Amoukou, et al.
0

While Shapley Values (SV) are one of the gold standard for interpreting machine learning models, we show that they are still poorly understood, in particular in the presence of categorical variables or of variables of low importance. For instance, we show that the popular practice that consists in summing the SV of dummy variables is false as it provides wrong estimates of all the SV in the model and implies spurious interpretations. Based on the identification of null and active coalitions, and a coalitional version of the SV, we provide a correct computation and inference of important variables. Moreover, a Python library (All the experiments and simulations can be reproduced with the publicly available library Active Coalition of Variables, https://www.github.com/salimamoukou/acv00) that computes reliably conditional expectations and SV for tree-based models, is implemented and compared with state-of-the-art algorithms on toy models and real data sets.

READ FULL TEXT

page 8

page 20

06/07/2021

Accurate and robust Shapley Values for explaining predictions and focusing on local important variables

Although Shapley Values (SV) are widely used in explainable AI, they can...
03/02/2022

py-irt: A Scalable Item Response Theory Library for Python

py-irt is a Python library for fitting Bayesian Item Response Theory (IR...
05/27/2020

Kernel methods library for pattern analysis and machine learning in python

Kernel methods have proven to be powerful techniques for pattern analysi...
02/01/2021

Computing the Hazard Ratios Associated with Explanatory Variables Using Machine Learning Models of Survival Data

Purpose: The application of Cox Proportional Hazards (CoxPH) models to s...
08/27/2021

DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning

We demonstrate a library for the integration of domain knowledge in deep...
08/13/2021

Data-driven advice for interpreting local and global model predictions in bioinformatics problems

Tree-based algorithms such as random forests and gradient boosted trees ...
05/18/2019

Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees

Tree ensembles, such as random forests and AdaBoost, are ubiquitous mach...