# Towards Interpretable Deep Neural Networks for Tabular Data

arXiv: https://arxiv.org/abs/2509.08617 · HTML: https://mlsanity.com/paper/2509.08617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Sparse autoencoder training and evaluation, one of 13 directions in Mechanistic interpretability.
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Placed in

- Mechanistic interpretability / [Sparse autoencoder training and evaluation](https://mlsanity.com/mechinterp/sparse-autoencoder-training-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors](https://mlsanity.com/paper/2103.15949/) (2021)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023](https://mlsanity.com/paper/2307.14338/) (2023)
- [T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction](https://mlsanity.com/paper/2211.16887/) (2022)
- [TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization](https://mlsanity.com/paper/2303.05506/) (2023)
- [ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data](https://mlsanity.com/paper/2306.12330/) (2023)
- [Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains](https://mlsanity.com/paper/2405.07414/) (2024)
- [InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation](https://mlsanity.com/paper/2406.00426/) (2024)

## Built on by (most cited first, 1 of 1)

- [XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders](https://mlsanity.com/paper/2512.13442/) (2025)

## Abstract (arXiv)

Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows us to represent predictions as linear combinations of semantically meaningful components. Empirical evaluations demonstrate that XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.