{"url":"/method/nam","slug":"nam","name":"NAM","full_name":"Neural Additive Model","full_name_withheld":false,"description_markdown":"**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). \r\n\r\nNAMs learn a linear combination of networks that each attend to a single input feature: each $f\\_{i}$ 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 $f\\_{i}\\left(x\\_{i}\\right)$ vs. $x\\_{i}$).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","paper":"/paper/neural-additive-models-interpretable-machine","first_author":"Rishabh Agarwal","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/neural-additive-models-interpretable-machine"},"source":{"url":"https://arxiv.org/abs/2004.13912v2","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/google-research/google-research/tree/master/neural_additive_models","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Interpretability","url":"/methods/category/interpretability","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Generalized Additive Models","url":"/methods/category/generalized-additive-models","pwc_aliases":[]}],"n_papers_tagged":18,"archive_num_papers":18,"papers_newest_first":[{"paper":null,"title":"NAM: A Normalization Attention Model for Personalized Product Search In Fliggy","date":"2025-06-10","arxiv_id":"2506.08382","n_code_links":0,"syntology":null},{"paper":null,"title":"Minimally Supervised Hierarchical Domain Intent Learning for CRS","date":"2025-05-04","arxiv_id":"2505.02209","n_code_links":0,"syntology":null},{"paper":null,"title":"MT-NAM: An Efficient and Adaptive Model for Epileptic Seizure Detection","date":"2025-03-11","arxiv_id":"2503.08251","n_code_links":0,"syntology":null},{"paper":null,"title":"Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset","date":"2024-12-25","arxiv_id":"2412.18839","n_code_links":0,"syntology":null},{"paper":null,"title":"Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models","date":"2024-07-26","arxiv_id":"2407.18541","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable Automatic Grading with Neural Additive Models","date":"2024-05-01","arxiv_id":"2405.00489","n_code_links":0,"syntology":null},{"paper":"/paper/gaussian-process-neural-additive-models","title":"Gaussian Process Neural Additive Models","date":"2024-02-19","arxiv_id":"2402.12518","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":"/paper/no-service-rail-surface-defect-segmentation","title":"No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interaction","date":"2023-06-27","arxiv_id":"2306.15442","n_code_links":1,"syntology":null},{"paper":null,"title":"Minimizing Energy Consumption in MU-MIMO via Antenna Muting by Neural Networks with Asymmetric Loss","date":"2023-06-08","arxiv_id":"2306.05162","n_code_links":0,"syntology":null},{"paper":"/paper/laplace-approximated-neural-additive-models","title":"Improving Neural Additive Models with Bayesian Principles","date":"2023-05-26","arxiv_id":"2305.16905","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Neural Attention Memory","date":"2023-02-18","arxiv_id":"2302.09422","n_code_links":0,"syntology":null},{"paper":null,"title":"Extending the Neural Additive Model for Survival Analysis with EHR Data","date":"2022-11-15","arxiv_id":"2211.07814","n_code_links":0,"syntology":null},{"paper":"/paper/higher-order-neural-additive-models-an","title":"Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions","date":"2022-09-30","arxiv_id":"2209.15409","n_code_links":1,"syntology":{"ran":0,"of":6,"unverified":6,"pointer_only":0}},{"paper":null,"title":"Neural Additive Models for Nowcasting","date":"2022-05-20","arxiv_id":"2205.10020","n_code_links":0,"syntology":null},{"paper":null,"title":"Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging","date":"2022-05-03","arxiv_id":"2205.01679","n_code_links":0,"syntology":null},{"paper":null,"title":"Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity","date":"2022-02-25","arxiv_id":"2202.12482","n_code_links":0,"syntology":null},{"paper":null,"title":"SurvNAM: The machine learning survival model explanation","date":"2021-04-18","arxiv_id":"2104.08903","n_code_links":0,"syntology":null},{"paper":"/paper/neural-additive-models-interpretable-machine","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","date":"2020-04-29","arxiv_id":"2004.13912","n_code_links":8,"syntology":{"ran":26,"of":33,"unverified":7,"pointer_only":14}}],"papers_shown":18,"tasks":[{"task":"/task/additive-models","name":"Additive models","papers":8},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":3},{"task":"/task/interpretable-machine-learning","name":"Interpretable Machine Learning","papers":3},{"task":"/task/decision-making","name":"Decision Making","papers":2},{"task":"/task/survival-analysis","name":"Survival Analysis","papers":2},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/clustering","name":"Clustering","papers":1},{"task":"/task/combinatorial-optimization","name":"Combinatorial Optimization","papers":1},{"task":"/task/conversational-recommendation","name":"Conversational Recommendation","papers":1},{"task":"/task/eeg-1","name":"EEG","papers":1},{"task":"/task/explainable-models","name":"Explainable Models","papers":1},{"task":"/task/explainable-artificial-intelligence","name":"Explainable artificial intelligence","papers":1},{"task":"/task/feature-engineering","name":"Feature Engineering","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/seizure-detection","name":"Seizure Detection","papers":1}],"tasks_shown":20,"n_tasks":35,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":5},{"year":"2023","papers":4},{"year":"2024","papers":4},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/nam"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}