DeepAI AI Chat
Log In Sign Up

Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model Agnostic Interpretations

by   Christian A. Scholbeck, et al.
Universität München

Non-linear machine learning models often trade off a great predictive performance for a lack of interpretability. However, model agnostic interpretation techniques now allow us to estimate the effect and importance of features for any predictive model. Different notations and terminology have complicated their understanding and how they are related. A unified view on these methods has been missing. We present the generalized SIPA (Sampling, Intervention, Prediction, Aggregation) framework of work stages for model agnostic interpretation techniques and demonstrate how several prominent methods for feature effects can be embedded into the proposed framework. We also formally introduce pre-existing marginal effects to describe feature effects for black box models. Furthermore, we extend the framework to feature importance computations by pointing out how variance-based and performance-based importance measures are based on the same work stages. The generalized framework may serve as a guideline to conduct model agnostic interpretations in machine learning.


page 10

page 14


Marginal Effects for Non-Linear Prediction Functions

Beta coefficients for linear regression models represent the ideal form ...

Visualizing the Feature Importance for Black Box Models

In recent years, a large amount of model-agnostic methods to improve the...

Shapley Decomposition of R-Squared in Machine Learning Models

In this paper we introduce a metric aimed at helping machine learning pr...

Conditional Feature Importance for Mixed Data

Despite the popularity of feature importance measures in interpretable m...

Model-agnostic interpretation by visualization of feature perturbations

Interpretation of machine learning models has become one of the most imp...

Spatial machine-learning model diagnostics: a model-agnostic distance-based approach

While significant progress has been made towards explaining black-box ma...

On Shapley Credit Allocation for Interpretability

We emphasize the importance of asking the right question when interpreti...