InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation

Jacob Yoke Hong Si, Wendy Yusi Cheng, Michael Cooper, Rahul Krishnan
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45353-45405, 2024.

Abstract

Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model’s efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-si24a, title = {{I}nterpre{T}ab{N}et: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation}, author = {Si, Jacob Yoke Hong and Cheng, Wendy Yusi and Cooper, Michael and Krishnan, Rahul}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {45353--45405}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/si24a/si24a.pdf}, url = {https://proceedings.mlr.press/v235/si24a.html}, abstract = {Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model’s efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.} }
Endnote
%0 Conference Paper %T InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation %A Jacob Yoke Hong Si %A Wendy Yusi Cheng %A Michael Cooper %A Rahul Krishnan %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-si24a %I PMLR %P 45353--45405 %U https://proceedings.mlr.press/v235/si24a.html %V 235 %X Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model’s efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.
APA
Si, J.Y.H., Cheng, W.Y., Cooper, M. & Krishnan, R.. (2024). InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:45353-45405 Available from https://proceedings.mlr.press/v235/si24a.html.

Related Material