# Stable and Interpretable Deep Learning for Tabular Data: Introducing InterpreTabNet with the Novel InterpreStability Metric

arXiv: https://arxiv.org/abs/2310.02870 · HTML: https://mlsanity.com/paper/2310.02870/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 11 of 11)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network](https://mlsanity.com/paper/1808.03314/) (2018)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](https://mlsanity.com/paper/1705.08741/) (2017)
- [Sparse Sequence-to-Sequence Models](https://mlsanity.com/paper/1905.05702/) (2019)
- [A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models](https://mlsanity.com/paper/1804.02969/) (2018)
- [An Equivalence of Fully Connected Layer and Convolutional Layer](https://mlsanity.com/paper/1712.01252/) (2017)
- [Lead-lag detection and network clustering for multivariate time series with an application to the US equity market](https://mlsanity.com/paper/2201.08283/) (2022)
- [LADDER: Latent Boundary-guided Adversarial Training](https://mlsanity.com/paper/2206.03717/) (2022)

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

- [A Survey on Deep Tabular Learning](https://mlsanity.com/paper/2410.12034/) (2024)

## Abstract (arXiv)

As Artificial Intelligence (AI) integrates deeper into diverse sectors, the quest for powerful models has intensified. While significant strides have been made in boosting model capabilities and their applicability across domains, a glaring challenge persists: many of these state-of-the-art models remain as black boxes. This opacity not only complicates the explanation of model decisions to end-users but also obstructs insights into intermediate processes for model designers. To address these challenges, we introduce InterpreTabNet, a model designed to enhance both classification accuracy and interpretability by leveraging the TabNet architecture with an improved attentive module. This design ensures robust gradient propagation and computational stability. Additionally, we present a novel evaluation metric, InterpreStability, which quantifies the stability of a model's interpretability. The proposed model and metric mark a significant stride forward in explainable models' research, setting a standard for transparency and interpretability in AI model design and application across diverse sectors. InterpreTabNet surpasses other leading solutions in tabular data analysis across varied application scenarios, paving the way for further research into creating deep-learning models that are both highly accurate and inherently explainable. The introduction of the InterpreStability metric ensures that the interpretability of future models can be measured and compared in a consistent and rigorous manner. Collectively, these contributions have the potential to promote the design principles and development of next-generation interpretable AI models, widening the adoption of interpretable AI solutions in critical decision-making environments.