iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data

arXiv:2608.04348 · cs.CV, cs.AI, cs.LG, stat.ML · Submitted 2026-08-05 · Read on arXiv

Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali, Gianfranco Doretto, Donald A. Adjeroh

cs.CV, cs.AI, cs.LG, stat.ML

Submitted: 2026-08-05

Comments: This paper has been accepted for presentation at the 28th International Conference on Pattern Recognition (ICPR 2026) in Lyon, France Code: https://github.com/zadid6pretam/iStructTab PyPI: pip install istructtab

Journal ref: International Conference on Pattern Recognition (ICPR 2026)

DOI: 10.1007/978-3-032-31404-8_43

Code: https://github.com/zadid6pretam/iStructTab

License: http://creativecommons.org/licenses/by/4.0/

The gist: Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalization problems.

Terminology

Abstract

Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalization problems. To tackle this challenge, we introduce Graph-Enhanced Descriptor Sequencing (GEDS), a structured feature sequencing algorithm grounded in principles from the Column Permutation Problem (CPP). GEDS refines statistical descriptors of the features through similarity graph-based computations, systematically determining an effective feature sequencing. We incorporate GEDS within an order-aware efficient transformer framework, utilizing order-aware memory tokens that explicitly adhere to the derived feature sequencing via a dedicated loss function. Experimental results across multimodal benchmarks demonstrate that iStructTab effectively minimizes feature dispersion, improving predictive performance and robustness, and highlighting the significance of structured feature sequencing in multimodal learning.

Sources

Related papers