# Structural Neural Additive Models: Enhanced Interpretable Machine Learning

arXiv: https://arxiv.org/abs/2302.09275 · HTML: https://mlsanity.com/paper/2302.09275/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [New insights and perspectives on the natural gradient method](https://mlsanity.com/paper/1412.1193/) (2014)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Interpretable machine learning: definitions, methods, and applications](https://mlsanity.com/paper/1901.04592/) (2019)
- [Limitations of the Empirical Fisher Approximation for Natural Gradient Descent](https://mlsanity.com/paper/1905.12558/) (2019)
- [Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach](https://mlsanity.com/paper/1806.01316/) (2018)
- [NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning](https://mlsanity.com/paper/2106.01613/) (2021)
- [GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions](https://mlsanity.com/paper/2003.07132/) (2020)
- [The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence](https://mlsanity.com/paper/2002.04806/) (2020)
- [M-FAC: Efficient Matrix-Free Approximations of Second-Order Information](https://mlsanity.com/paper/2107.03356/) (2021)
- [On the Variance of the Fisher Information for Deep Learning](https://mlsanity.com/paper/2107.04205/) (2021)
- [Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean](https://mlsanity.com/paper/2301.11862/) (2023)
- [Adaptive spline fitting with particle swarm optimization](https://mlsanity.com/paper/1907.12160/) (2019)

## Built on by (most cited first, 6 of 6)

- [Improving Neural Additive Models with Bayesian Principles](https://mlsanity.com/paper/2305.16905/) (2023)
- [Explainable Automatic Grading with Neural Additive Models](https://mlsanity.com/paper/2405.00489/) (2024)
- [Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks](https://mlsanity.com/paper/2504.08712/) (2025)
- [DNAMite: Interpretable Calibrated Survival Analysis with Discretized Additive Models](https://mlsanity.com/paper/2411.05923/) (2024)
- [textttfindr: Transparent and Fair Credit Risk Decisions through Semi-Structured Regressions](https://mlsanity.com/paper/2608.24582/) (2026)
- [From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning](https://mlsanity.com/paper/2604.05635/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power. There has been extensive research on how DNNs arrive at their decisions, however, the inherently uninterpretable networks remain up to this day mostly unobservable "black boxes". In recent years, the field has seen a push towards interpretable neural networks, such as the visually interpretable Neural Additive Models (NAMs). We propose a further step into the direction of intelligibility beyond the mere visualization of feature effects and propose Structural Neural Additive Models (SNAMs). A modeling framework that combines classical and clearly interpretable statistical methods with the predictive power of neural applications. Our experiments validate the predictive performances of SNAMs. The proposed framework performs comparable to state-of-the-art fully connected DNNs and we show that SNAMs can even outperform NAMs while remaining inherently more interpretable.