# Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks

arXiv: https://arxiv.org/abs/2504.08712 · HTML: https://mlsanity.com/paper/2504.08712/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [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)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [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)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [On Embeddings for Numerical Features in Tabular Deep Learning](https://mlsanity.com/paper/2203.05556/) (2022)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [On Identifiability in Transformers](https://mlsanity.com/paper/1908.04211/) (2019)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data](https://mlsanity.com/paper/2407.04491/) (2024)
- [NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning](https://mlsanity.com/paper/2106.01613/) (2021)
- [Neural Basis Models for Interpretability](https://mlsanity.com/paper/2205.14120/) (2022)
- [Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection](https://mlsanity.com/paper/2209.09326/) (2022)
- [Scalable Interpretability via Polynomials](https://mlsanity.com/paper/2205.14108/) (2022)
- [Semi-Structured Distributional Regression -- Extending Structured Additive Models by Arbitrary Deep Neural Networks and Data Modalities](https://mlsanity.com/paper/2002.05777/) (2020)
- [Mambular: A Sequential Model for Tabular Deep Learning](https://mlsanity.com/paper/2408.06291/) (2024)
- [Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean](https://mlsanity.com/paper/2301.11862/) (2023)
- [Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models](https://mlsanity.com/paper/2305.11475/) (2023)
- [Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions](https://mlsanity.com/paper/2209.15409/) (2022)
- [On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning](https://mlsanity.com/paper/2411.17207/) (2024)
- [Structural Neural Additive Models: Enhanced Interpretable Machine Learning](https://mlsanity.com/paper/2302.09275/) (2023)
- [Neural Additive Image Model: Interpretation through Interpolation](https://mlsanity.com/paper/2405.02295/) (2024)

## Built on by (most cited first, 2 of 2)

- [EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models](https://mlsanity.com/paper/2601.08556/) (2026)
- [PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models](https://mlsanity.com/paper/2609.23574/) (2026)

## Abstract (arXiv)

In recent years, deep neural networks have showcased their predictive power across a variety of tasks. Beyond natural language processing, the transformer architecture has proven efficient in addressing tabular data problems and challenges the previously dominant gradient-based decision trees in these areas. However, this predictive power comes at the cost of intelligibility: Marginal feature effects are almost completely lost in the black-box nature of deep tabular transformer networks. Alternative architectures that use the additivity constraints of classical statistical regression models can maintain intelligible marginal feature effects, but often fall short in predictive power compared to their more complex counterparts. To bridge the gap between intelligibility and performance, we propose an adaptation of tabular transformer networks designed to identify marginal feature effects. We provide theoretical justifications that marginal feature effects can be accurately identified, and our ablation study demonstrates that the proposed model efficiently detects these effects, even amidst complex feature interactions. To demonstrate the model's predictive capabilities, we compare it to several interpretable as well as black-box models and find that it can match black-box performances while maintaining intelligibility. The source code is available at https://github.com/OpenTabular/NAMpy.