Research map / Learning theory and algorithms / Prediction and decision losses
Neural Additive Models: Interpretable Machine Learning with Neural Nets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| NAMs instead of logistic regression | interpretable models · MIMIC-II | AUC: 0.791 -> 0.830 | Helped |
| NAMs instead of tree-based GAM (EBMs) | interpretable GAMs · MIMIC-II | AUC: 0.835 -> 0.830 | No clear effect |
| NAMs instead of unconstrained DNN | tabular regression · CA Housing | RMSE: 0.492 -> 0.562 | Hurt |
| multitask NAM instead of single-task NAMs (ablation) | NAM · synthetic multitask | MSE: 1.083 -> 0.712 | Helped |
| multitask NAM (by gender) instead of single-task (ablation) | NAM · COMPAS Combined | ROC AUC: 0.737 -> 0.739 | No clear effect |
| ExU hidden units instead of standard DNN feature nets (ablation) | NAM · Credit | AUC: ~0.974 -> 0.980 | Helped |
Closest papers by meaning
- Improving Neural Additive Models with Bayesian Principles (ICML 2024 · similarity 0.88)
- Gaussian Process Neural Additive Models (AAAI 2024 · similarity 0.85)
- Additive Models Explained: A Computational Complexity Approach (NeurIPS 2025 · similarity 0.83)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.82)
- The Intelligible and Effective Graph Neural Additive Network (NeurIPS 2024 · similarity 0.81)
- Data-Efficient Learning with Neural Programs (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.