Methods › General › Interpretability › NAM
Neural Additive Model
NAM
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).
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.
-
NAM: A Normalization Attention Model for Personalized Product Search In Fliggy 10 Jun 2025 · 0 repositories · arXiv:2506.08382
-
Minimally Supervised Hierarchical Domain Intent Learning for CRS 4 May 2025 · 0 repositories · arXiv:2505.02209
-
MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection 11 Mar 2025 · 0 repositories · arXiv:2503.08251
-
Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset 25 Dec 2024 · 0 repositories · arXiv:2412.18839
-
Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models 26 Jul 2024 · 0 repositories · arXiv:2407.18541
-
Explainable Automatic Grading with Neural Additive Models 1 May 2024 · 0 repositories · arXiv:2405.00489
-
Gaussian Process Neural Additive Models 19 Feb 2024 · 1 repository · arXiv:2402.12518Syntology ran 1 of 1 samples · 0 unverified
-
No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interaction 27 Jun 2023 · 1 repository · arXiv:2306.15442
-
Minimizing Energy Consumption in MU-MIMO via Antenna Muting by Neural Networks with Asymmetric Loss 8 Jun 2023 · 0 repositories · arXiv:2306.05162
-
Improving Neural Additive Models with Bayesian Principles 26 May 2023 · 1 repository · arXiv:2305.16905Syntology ran 0 of 3 samples · 3 unverified
-
Neural Attention Memory 18 Feb 2023 · 0 repositories · arXiv:2302.09422
-
Extending the Neural Additive Model for Survival Analysis with EHR Data 15 Nov 2022 · 0 repositories · arXiv:2211.07814
-
Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions 30 Sep 2022 · 1 repository · arXiv:2209.15409Syntology ran 0 of 6 samples · 6 unverified
-
Neural Additive Models for Nowcasting 20 May 2022 · 0 repositories · arXiv:2205.10020
-
Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging 3 May 2022 · 0 repositories · arXiv:2205.01679
-
Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity 25 Feb 2022 · 0 repositories · arXiv:2202.12482
-
SurvNAM: The machine learning survival model explanation 18 Apr 2021 · 0 repositories · arXiv:2104.08903
-
Neural Additive Models: Interpretable Machine Learning with Neural Nets 29 Apr 2020 · 8 repositories · arXiv:2004.13912Syntology ran 26 of 33 samples · 7 unverified · 14 pointer-only (licence)
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.
Usage over time archive 2025-07-28
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
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