# Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection

arXiv: https://arxiv.org/abs/2209.09326 · HTML: https://mlsanity.com/paper/2209.09326/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 19 Sep 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [The Shapley Taylor Interaction Index](https://mlsanity.com/paper/1902.05622/) (2019)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [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)
- [How does this interaction affect me? Interpretable attribution for feature interactions](https://mlsanity.com/paper/2006.10965/) (2020)
- [How Interpretable and Trustworthy are GAMs?](https://mlsanity.com/paper/2006.06466/) (2020)
- [Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity](https://mlsanity.com/paper/2202.12482/) (2022)
- [Additive Approximations in High Dimensional Nonparametric Regression via the SALSA](https://mlsanity.com/paper/1602.00287/) (2016)
- [Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning](https://mlsanity.com/paper/2105.02410/) (2021)
- [Learning Sparse Additive Models with Interactions in High Dimensions](https://mlsanity.com/paper/1604.05307/) (2016)
- [Creating Powerful and Interpretable Models with Regression Networks](https://mlsanity.com/paper/2107.14417/) (2021)

## Built on by (most cited first, 28 of 28)

- [TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting](https://mlsanity.com/paper/2310.04948/) (2023)
- [Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean](https://mlsanity.com/paper/2301.11862/) (2023)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning](https://mlsanity.com/paper/2402.02334/) (2024)
- [Regionally Additive Models: Explainable-by-design models minimizing feature interactions](https://mlsanity.com/paper/2309.12215/) (2023)
- [Challenges in interpretability of additive models](https://mlsanity.com/paper/2504.10169/) (2025)
- [Additive Models Explained: A Computational Complexity Approach](https://mlsanity.com/paper/2510.21292/) (2025)
- [Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network](https://mlsanity.com/paper/2310.15342/) (2023)
- [Transparent Networks for Multivariate Time Series](https://mlsanity.com/paper/2410.10535/) (2024)
- [A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection](https://mlsanity.com/paper/2410.11964/) (2024)
- [Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks](https://mlsanity.com/paper/2504.08712/) (2025)
- [Tree-like Pairwise Interaction Networks](https://mlsanity.com/paper/2508.15678/) (2025)
- [Higher-Order Causal Structure Learning with Additive Models](https://mlsanity.com/paper/2511.03831/) (2025)
- [Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models](https://mlsanity.com/paper/2604.13332/) (2026)
- [Neural Additive Image Model: Interpretation through Interpolation](https://mlsanity.com/paper/2405.02295/) (2024)
- [Discovering Car-following Dynamics from Trajectory Data through Deep Learning](https://mlsanity.com/paper/2408.00251/) (2024)
- [GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning](https://mlsanity.com/paper/2410.04560/) (2024)
- [Generalized Sparse Additive Model with Unknown Link Function](https://mlsanity.com/paper/2410.06012/) (2024)
- [SPARLING: Learning Latent Representations with Extremely Sparse Activations](https://mlsanity.com/paper/2302.01976/) (2023)
- [Fast and interpretable Support Vector Classification based on the truncated ANOVA decomposition](https://mlsanity.com/paper/2402.02438/) (2024)
- [PE: A Poincare Explanation Method for Fast Text Hierarchy Generation](https://mlsanity.com/paper/2403.16554/) (2024)
- [HRR: Hierarchical Retrospection Refinement for Generated Image Detection](https://mlsanity.com/paper/2502.17862/) (2025)
- [Multiplicative-Additive Constrained Models:Toward Joint Visualization of Interactive and Independent Effects](https://mlsanity.com/paper/2509.21923/) (2025)
- [Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability](https://mlsanity.com/paper/2509.23068/) (2025)
- [Additive Large Language Models for Semi-Structured Text](https://mlsanity.com/paper/2511.11922/) (2025)
- [EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models](https://mlsanity.com/paper/2601.08556/) (2026)
- [Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity](https://mlsanity.com/paper/2602.10585/) (2026)
- [TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data](https://mlsanity.com/paper/2609.20693/) (2026)

## Abstract (arXiv)

There is currently a large gap in performance between the statistically rigorous methods like linear regression or additive splines and the powerful deep methods using neural networks. Previous works attempting to close this gap have failed to fully investigate the exponentially growing number of feature combinations which deep networks consider automatically during training. In this work, we develop a tractable selection algorithm to efficiently identify the necessary feature combinations by leveraging techniques in feature interaction detection. Our proposed Sparse Interaction Additive Networks (SIAN) construct a bridge from these simple and interpretable models to fully connected neural networks. SIAN achieves competitive performance against state-of-the-art methods across multiple large-scale tabular datasets and consistently finds an optimal tradeoff between the modeling capacity of neural networks and the generalizability of simpler methods.