mlsanityData to 14 Oct 2026

Conditional expectation network for SHAP

arXiv 2307.10654 ↗First posted 20 Jul 2023cs.LG cs.CE stat.APcited by 0

Not on the map. Why?

Abstract (arXiv)

A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the latter is also known as interventional SHAP). Except for tree-based methods, usually the unconditional version is used (for computational reasons). We provide a (surrogate) neural network approach which allows us to efficiently calculate the conditional version for both neural networks and other regression models, and which properly considers the dependence structure in the feature components. This proposal is also useful to provide drop1 and anova analyses in complex regression models which are similar to their generalized linear model (GLM) counterparts, and we provide a partial dependence plot (PDP) counterpart that considers the right dependence structure in the feature components.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 41 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

12 of 41 references.

References · 12

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2019The many Shapley values for model explanationcited by 344
  4. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 213
  5. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  6. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  7. 2016Entity Embeddings of Categorical Variablescited by 87
  8. 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 69
  9. 2021Regression Diagnostics meets Forecast Evaluation: Conditional Calibration, Reliability Diagrams, and Coefficient of Determinationcited by 31
  10. 2015Artificial Neural Networks Applied to Taxi Destination Predictioncited by 18
  11. 2022Unifying local and global model explanations by functional decomposition of low dimensional structurescited by 18
  12. 2022Understanding Interventional TreeSHAP : How and Why it Workscited by 2

Built on by

Not cited yet.