English

DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data

Machine Learning 2026-05-06 v1 Artificial Intelligence

Abstract

High-dimensional tabular data lacks a natural feature order, limiting the applicability of permutation-sensitive deep learning models. We propose DynaTab, a dynamic feature ordering-enabled architecture inspired by neural rewiring. We introduce a lightweight criterion that predicts when feature permutation will benefit a dataset by quantifying its intrinsic complexity. DynaTab dynamically reorders features via a neural rewiring algorithm and processes them through a compact, dynamic order-aware combination of separate learned positional embedding, importance-based gating, and masked attention layers, compatible with any sequence-sensitive backbone. Trained end-to-end with bespoke dynamic feature ordering (DFO) and dispersion losses, DynaTab achieves statistically significant gains, particularly on high-dimensional datasets, where it is benchmarked against 45 state-of-the-art baselines across 36 different real-world tabular datasets. Our results position DynaTab as a compelling new paradigm for high-dimensional tabular deep learning.

Keywords

Cite

@article{arxiv.2605.03430,
  title  = {DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data},
  author = {Al Zadid Sultan Bin Habib and Gianfranco Doretto and Donald A. Adjeroh},
  journal= {arXiv preprint arXiv:2605.03430},
  year   = {2026}
}

Comments

This paper has been accepted for archival publication in the PMLR proceedings of the AAAI 2026 Neuro for AI \& AI for Neuro: Towards Multi-Modal Natural Intelligence (NeuroAI) Workshop, Code: https://github.com/zadid6pretam/DynaTab, PyPI: pip install dynatab

R2 v1 2026-07-01T12:49:56.545Z