Mambular: A Sequential Model for Tabular Deep Learning

Anton Frederik Thielmann, Manish Kumar, Christoph Weisser, Arik Reuter, Benjamin Säfken +1 more
8/12/2024
cs.LG

No official code found. Best implementation: OpenTabular/DeepTab (321 stars, MIT, last commit 2026-05-03).

Abstract

The analysis of tabular data has traditionally been dominated by gradient-boosted decision trees (GBDTs), known for their proficiency with mixed categorical and numerical features. However, recent deep learning innovations are challenging this dominance. This paper investigates the use of autoregressive state-space models for tabular data and compares their performance against established benchmark models. Additionally, we explore various adaptations of these models, including different pooling strategies, feature interaction mechanisms, and bi-directional processing techniques to understand their effectiveness for tabular data. Our findings indicate that interpreting features as a sequence and processing them and their interactions through structured state-space layers can lead to significant performance improvement. This research underscores the versatility of autoregressive models in tabular data analysis, positioning them as a promising alternative that could substantially enhance deep learning capabilities in this traditionally challenging area. The source code is available at https://github.com/basf/mamba-tabular.

View on arXivView PDF

Code Implementations(1)

OpenTabular/DeepTabCommunity100%
MIT

DeepTab is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mambular, TabM, FT-Transformer, TabulaRNN, TabTransformer, and tabular ResNets.

32125Just, PythonMay 3, 20245 months agoMIT
classificationdeeplearningdistributional-regressionft-transformermamba+12 more

Similar Papers

Deep Learning within Tabular Data: Foundations, Challenges, Advances and Future Directions

85% match2025

A Survey on Deep Tabular Learning

84% match2024

Deep Learning with Tabular Data: A Self-supervised Approach

84% match1 repo42024

Transformers with Stochastic Competition for Tabular Data Modelling

83% match1 repo42024

TabArena: A Living Benchmark for Machine Learning on Tabular Data

82% match1 repo3332025

TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling

82% match2 repos1.1k2024

Cite this paper

@article{thielmann2024mambular,
  title  = {Mambular: A Sequential Model for Tabular Deep Learning},
  author = {Anton Frederik Thielmann and Manish Kumar and Christoph Weisser and Arik Reuter and Benjamin Säfken and Soheila Samiee},
  year   = {2024},
  eprint = {2408.06291},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.06291v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.06291.svg)](https://codeofpaper.com/paper/2408.06291)

Discussion