Feature attributions based on the Shapley value are popular for explaining machine
learning models. However, their estimation is complex from both theoretical and …

Nowadays, deep neural networks are widely used in mission critical systems such as
healthcare, self-driving vehicles, and military which have direct impact on human lives …

Explainable machine learning offers the potential to provide stakeholders with insights into
model behavior by using various methods such as feature importance scores, counterfactual …

Researchers have proposed a wide variety of model explanation approaches, but it remains
unclear how most methods are related or when one method is preferable to another. We …

Game-theoretic formulations of feature importance have become popular as a way to"
explain" machine learning models. These methods define a cooperative game between the …

The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a
large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for …

Understanding the inner workings of complex machine learning models is a long-standing
problem and most recent research has focused on local interpretability. To assess the role of …

We discuss promising recent contributions on quantifying feature relevance using Shapley
values, where we observed some confusion on which probability distribution is the right one …

SHAP explanations are a popular feature-attribution mechanism for explainable AI. They
use game-theoretic notions to measure the influence of individual features on the prediction …

Despite a sea of interpretability methods that can produce plausible explanations, the field
has also empirically seen many failure cases of such methods. In light of these results, it …