Methods › General › Interpretability › NAM

Neural Additive Model

NAM

18 papers tagged archive 2025-07-28

Introduced by Rishabh Agarwal et al. in Neural Additive Models: Interpretable Machine Learning with Neural Nets

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Neural Additive Models (NAMs) make restrictions on the structure of neural networks, which yields a family of models that are inherently interpretable while suffering little loss in prediction accuracy when applied to tabular data. Methodologically, NAMs belong to a larger model family called Generalized Additive Models (GAMs).

NAMs learn a linear combination of networks that each attend to a single input feature: each fᵢ in the traditional GAM formulationis parametrized by a neural network. These networks are trained jointly using backpropagation and can learn arbitrarily complex shape functions. Interpreting NAMs is easy as the impact of a feature on the prediction does not rely on the other features and can be understood by visualizing its corresponding shape function (e.g., plotting fᵢ(xᵢ) vs. xᵢ).

PaperSourceSee Code · google-research/google-research

Papers archive 2025-07-28

18 shown of 18, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 35 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Additive models8
BIG-bench Machine Learning3
Interpretable Machine Learning3
Decision Making2
Survival Analysis2
Bayesian Inference1
Classification1
Clustering1
Combinatorial Optimization1
Conversational Recommendation1
EEG1
Explainable Models1
Explainable artificial intelligence1
Feature Engineering1
Few-Shot Learning1
GPU1
Image Segmentation1
Recommendation Systems1
Segmentation1
Seizure Detection1

Usage over time archive 2025-07-28

Papers per year tagged with NAM: 2020 to 2025, peak 5 5 0 2020: 1 paper 2020 2021: 1 paper 2021 2022: 5 papers 2022 2023: 4 papers 2023 2024: 4 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (18 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

InterpretabilityGeneralized Additive Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections