mlsanityData to 14 Oct 2026

Improving Neural Additive Models with Bayesian Principles

arXiv 2305.16905 ↗First posted 26 May 2023stat.ML cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Neural additive models (NAMs) enhance the transparency of deep neural networks by handling input features in separate additive sub-networks. However, they lack inherent mechanisms that provide calibrated uncertainties and enable selection of relevant features and interactions. Approaching NAMs from a Bayesian perspective, we augment them in three primary ways, namely by a) providing credible intervals for the individual additive sub-networks; b) estimating the marginal likelihood to perform an implicit selection of features via an empirical Bayes procedure; and c) facilitating the ranking of feature pairs as candidates for second-order interaction in fine-tuned models. In particular, we develop Laplace-approximated NAMs (LA-NAMs), which show improved empirical performance on tabular datasets and challenging real-world medical tasks.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 56 of its 111 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

56 of 111 references.

References · 56

  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. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
  8. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 796
  9. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  10. 2015Weight Uncertainty in Neural Networkscited by 554
  11. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  12. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
38 more
  1. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
  2. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  3. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  4. 2017The Expressive Power of Neural Networks: A View from the Widthcited by 320
  5. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  6. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  7. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 246
  8. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 199
  9. 2019Practical Deep Learning with Bayesian Principlescited by 158
  10. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  11. 2021Bayesian Neural Network Priors Revisitedcited by 121
  12. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 106
  13. 2021Repulsive Deep Ensembles are Bayesiancited by 104
  14. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  15. 2020Bayesian Deep Ensembles via the Neural Tangent Kernelcited by 90
  16. 2019Approximate Inference Turns Deep Networks into Gaussian Processescited by 89
  17. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 87
  18. 2020PACOH: Bayes-Optimal Meta-Learning with PAC-Guaranteescited by 85
  19. 2016Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriorscited by 82
  20. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  21. 2017Detecting Statistical Interactions from Neural Network Weightscited by 80
  22. 2019'In-Between' Uncertainty in Bayesian Neural Networkscited by 80
  23. 2018Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Makingcited by 67
  24. 2022Better Uncertainty Calibration via Proper Scores for Classification and Beyondcited by 65
  25. 2022Neural Basis Models for Interpretabilitycited by 56
  26. 2022Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximationscited by 42
  27. 2019Function Space Particle Optimization for Bayesian Neural Networkscited by 41
  28. 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 39
  29. 2021Data augmentation in Bayesian neural networks and the cold posterior effectcited by 36
  30. 2021Exact Langevin Dynamics with Stochastic Gradientscited by 30
  31. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
  32. 2022Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsitycited by 25
  33. 2021Last Layer Marginal Likelihood for Invariance Learningcited by 21
  34. 2021On Stein Variational Neural Network Ensemblescited by 21
  35. 2021BNNpriors: A library for Bayesian neural network inference with different prior distributionscited by 20
  36. 2022Calibration tests beyond classificationcited by 20
  37. 2022Additive Gaussian Processes Revisitedcited by 19
  38. 2023Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Meancited by 18

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 6.

15 papers.

Sort:

  1. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  2. 2024Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihoodcited by 7
  3. 2025Challenges in interpretability of additive modelscited by 3
  4. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  5. 2024Explainable Interface for Human-Autonomy Teaming: A Surveycited by 2
  6. 2024NBMLSS: probabilistic forecasting of electricity prices via Neural Basis Models for Location Scale and Shapecited by 2
  7. 2026Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Modelscited by 2
  8. 2024GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learningcited by 1
  9. 2026Provably Explaining Neural Additive Modelscited by 1
  10. 2025LucidAtlas: Learning Uncertainty-Aware, Covariate-Disentangled, Individualized Atlas Representationscited by 0
  11. 2025From Distributional to Quantile Neural Basis Models: the case of Electricity Price Forecastingcited by 0
  12. 2026EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Modelscited by 0
3 more
  1. 2026Neural Additive Experts: Context-Gated Experts for Controllable Model Additivitycited by 0
  2. 2026Joint Model and Data Sparsification via the Marginal Likelihoodcited by 0
  3. 2026The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networkscited by 0