mlsanityData to 7 Oct 2026

NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning

arXiv 2106.01613 ↗First posted 3 Jun 2021cs.LGcited by 88

Not on the map. Why?

Abstract (arXiv)

Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of interpretable models with a long history of use in these high-risk domains, but they lack desirable features of deep learning such as differentiability and scalability. In this work, we propose a neural GAM (NODE-GAM) and neural GA2M (NODE-GA2M) that scale well and perform better than other GAMs on large datasets, while remaining interpretable compared to other ensemble and deep learning models. We demonstrate that our models find interesting patterns in the data. Lastly, we show that we improve model accuracy via self-supervised pre-training, an improvement that is not possible for non-differentiable GAMs.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 3 Jun 2021.

Builds on

15 of 38 references.

References · 15

  1. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  2. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  3. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  4. 2020Concept Bottleneck Modelscited by 1,022
  5. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  6. 2019Attention is not not Explanationcited by 629
  7. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  8. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
  9. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  10. 2019Sparse Sequence-to-Sequence Modelscited by 167
  11. 2017Detecting Statistical Interactions from Neural Network Weightscited by 80
  12. 2017Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillationcited by 62
3 more
  1. 2018Quasi-hyperbolic momentum and Adam for deep learningcited by 47
  2. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  3. 2019Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Modelscited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 11; 2023: 13; 2024: 25; 2025: 17; 2026: 20.

88 papers.

Sort:

By area:

  1. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 65
  2. 2022Neural Basis Models for Interpretabilitycited by 56
  3. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 46
  4. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  5. 2022Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selectioncited by 28
  6. 2024Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Latercited by 28
  7. 2022Scalable Interpretability via Polynomialscited by 25
  8. 2023Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Meancited by 18
  9. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  10. 2022Interpretable Mixture of Expertscited by 17
  11. 2022Data-Efficient and Interpretable Tabular Anomaly Detectioncited by 15
  12. 2023Backpack Language Modelscited by 15
38 more
  1. 2023Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Modelscited by 12
  2. 2023GradTree: Learning Axis-Aligned Decision Trees with Gradient Descentcited by 11
  3. 2024Gaussian Process Neural Additive Modelscited by 11
  4. 2023GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Datacited by 10
  5. 2023Unlocking the Transferability of Tokens in Deep Models for Tabular Datacited by 8
  6. 2022Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactionscited by 7
  7. 2022Interpretability with full complexity by constraining feature informationcited by 7
  8. 2022TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasetscited by 6
  9. 2023Structural Neural Additive Models: Enhanced Interpretable Machine Learningcited by 6
  10. 2023Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Modelscited by 6
  11. 2024CAT: Interpretable Concept-based Taylor Additive Modelscited by 5
  12. 2024Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimizationcited by 5
  13. 2024The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanationscited by 5
  14. 2023A Survey of Explainable AI in Deep Visual Modeling: Methods and Metricscited by 4
  15. 2023Interpretable Reinforcement Learning via Neural Additive Models for Inventory Managementcited by 4
  16. 2024Scalable Higher-Order Tensor Product Spline Modelscited by 4
  17. 2025Tensor Product Neural Networks for Functional ANOVA Modelcited by 4
  18. 2021Attention-like feature explanation for tabular datacited by 3
  19. 2023Regionally Additive Models: Explainable-by-design models minimizing feature interactionscited by 3
  20. 2024NeurCAM: Interpretable Neural Clustering via Additive Modelscited by 3
  21. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  22. 2026Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architecturescited by 3
  23. 2024Interpretable Prediction and Feature Selection for Survival Analysiscited by 2
  24. 2024How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regressioncited by 2
  25. 2024META-ANOVA: Screening interactions for interpretable machine learningcited by 2
  26. 2024ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learningcited by 2
  27. 2024Transparent Networks for Multivariate Time Seriescited by 2
  28. 2025Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networkscited by 2
  29. 2026Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regressioncited by 2
  30. 2022Additive Higher-Order Factorization Machinescited by 1
  31. 2023DeepROCK: Error-controlled interaction detection in deep neural networkscited by 1
  32. 2024Interpretable Short-Term Load Forecasting via Multi-Scale Temporal Decompositioncited by 1
  33. 2024Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equationscited by 1
  34. 2024Neural Additive Image Model: Interpretation through Interpolationcited by 1
  35. 2024Linear Mode Connectivity in Differentiable Tree Ensemblescited by 1
  36. 2024How Video Meetings Change Your Expressioncited by 1
  37. 2024GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learningcited by 1
  38. 2024Generalized Sparse Additive Model with Unknown Link Functioncited by 1

50 most cited of 88 All 88 (JSON)