mlsanityData to 14 Oct 2026

Challenges in interpretability of additive models

arXiv 2504.10169 ↗First posted 14 Apr 2025cs.LG stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ``interpretability'' or ``suitability for safety-critical applications'' of such models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 33 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

14 of 33 references.

References · 14

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2016The Mythos of Model Interpretabilitycited by 721
  4. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  5. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  6. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  7. 2022Neural Basis Models for Interpretabilitycited by 56
  8. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  9. 2023Exploring and Interacting with the Set of Good Sparse Generalized Additive Modelscited by 30
  10. 2022Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selectioncited by 28
  11. 2022Additive Gaussian Processes Revisitedcited by 19
  12. 2023Improving Neural Additive Models with Bayesian Principlescited by 15
2 more
  1. 2023Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Modelscited by 12
  2. 2014Fused Lasso Additive Modelcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Makingcited by 1
  2. 2025From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecastingcited by 0
  3. 2026Controlling for Omitted Variable Bias in Deep Neural Networkscited by 0