A Unified Approach to Interpreting Model Predictions

Apr 19, 2019 - 9:30 am to 10:30 am

SLAC, Kavli 3rd Floor Conf. Room

Sowmya Kamath

Join us Friday April 19th for the latest edition of the KIPAC Stats & ML Journal Club. We'll meet at 9:30 on the Kavli Building at SLAC (or on Zoom). This week's discussion will be led by Sowmya Kamath, and the subject will be the SHAP framework, a generic framework for model interpretation. Please see the link and abstract below. See you there!



A Unified Approach to Interpreting Model Predictions

Understanding why a model makes a certain prediction can be as crucial as the

prediction’s accuracy in many applications. However, the highest accuracy for large

modern datasets is often achieved by complex models that even experts struggle to

interpret, such as ensemble or deep learning models, creating a tension between

accuracy and interpretability. In response, various methods have recently been

proposed to help users interpret the predictions of complex models, but it is often

unclear how these methods are related and when one method is preferable over

another. To address this problem, we present a unified framework for interpreting

predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature

an importance value for a particular prediction. Its novel components include: (1)

the identification of a new class of additive feature importance measures, and (2)

theoretical results showing there is a unique solution in this class with a set of

desirable properties. The new class unifies six existing methods, notable because

several recent methods in the class lack the proposed desirable properties. Based

on insights from this unification, we present new methods that show improved

computational performance and/or better consistency with human intuition than

previous approaches.