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

Al Zadid Sultan Bin Habib, Gianfranco Doretto, Donald A. Adjeroh
Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, PMLR 308:27-57, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v308-habib26a, title = {DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data}, author = {Habib, Al Zadid Sultan Bin and Doretto, Gianfranco and Adjeroh, Donald A.}, booktitle = {Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026}, pages = {27--57}, year = {2026}, editor = {Abbasi-Asl, Reza and Iqbal, Asim and Ito, Shinya and Arkhipov, Anton and Sanborn, Sophia}, volume = {308}, series = {Proceedings of Machine Learning Research}, month = {27 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v308/main/assets/habib26a/habib26a.pdf}, url = {https://proceedings.mlr.press/v308/habib26a.html}, 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.} }
Endnote
%0 Conference Paper %T DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data %A Al Zadid Sultan Bin Habib %A Gianfranco Doretto %A Donald A. Adjeroh %B Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026 %C Proceedings of Machine Learning Research %D 2026 %E Reza Abbasi-Asl %E Asim Iqbal %E Shinya Ito %E Anton Arkhipov %E Sophia Sanborn %F pmlr-v308-habib26a %I PMLR %P 27--57 %U https://proceedings.mlr.press/v308/habib26a.html %V 308 %X 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.
APA
Habib, A.Z.S.B., Doretto, G. & Adjeroh, D.A.. (2026). DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data. Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, in Proceedings of Machine Learning Research 308:27-57 Available from https://proceedings.mlr.press/v308/habib26a.html.

Related Material