mlsanityData to 7 Oct 2026

The Berkelmans-Pries Feature Importance Method: A Generic Measure of Informativeness of Features

arXiv 2301.04740 ↗First posted 11 Jan 2023cs.LG cs.GT math.STcited by 0

Not on the map. Why?

Abstract (arXiv)

Over the past few years, the use of machine learning models has emerged as a generic and powerful means for prediction purposes. At the same time, there is a growing demand for interpretability of prediction models. To determine which features of a dataset are important to predict a target variable Y, a Feature Importance (FI) method can be used. By quantifying how important each feature is for predicting Y, irrelevant features can be identified and removed, which could increase the speed and accuracy of a model, and moreover, important features can be discovered, which could lead to valuable insights. A major problem with evaluating FI methods, is that the ground truth FI is often unknown. As a consequence, existing FI methods do not give the exact correct FI values. This is one of the many reasons why it can be hard to properly interpret the results of an FI method. Motivated by this, we introduce a new global approach named the Berkelmans-Pries FI method, which is based on a combination of Shapley values and the Berkelmans-Pries dependency function. We prove that our method has many useful properties, and accurately predicts the correct FI values for several cases where the ground truth FI can be derived in an exact manner. We experimentally show for a large collection of FI methods (468) that existing methods do not have the same useful properties. This shows that the Berkelmans-Pries FI method is a highly valuable tool for analyzing datasets with complex interdependencies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 61 references that are in the map. First posted on arXiv 11 Jan 2023.

Builds on

21 of 61 references.

References · 21

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  5. 2019The many Shapley values for model explanationcited by 341
  6. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  7. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  8. 2019The Shapley Taylor Interaction Indexcited by 143
  9. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  10. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  11. 2018Visualizing the Feature Importance for Black Box Modelscited by 55
  12. 2018DeepPINK: reproducible feature selection in deep neural networkscited by 41
9 more
  1. 2020Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approachcited by 37
  2. 2019Unbiased Measurement of Feature Importance in Tree-Based Methodscited by 30
  3. 2019A Debiased MDI Feature Importance Measure for Random Forestscited by 24
  4. 2022Faking feature importance: A cautionary tale on the use of differentially-private synthetic datacited by 8
  5. 2021Information Theoretic Measures for Fairness-aware Feature Selectioncited by 4
  6. 2021Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semanticscited by 3
  7. 2021Inferring feature importance with uncertainties in high-dimensional datacited by 2
  8. 2020FSinR: an exhaustive package for feature selectioncited by 1
  9. 2022The BP Dependency Function: a Generic Measure of Dependence between Random Variablescited by 1

Built on by

Not cited yet.