iLTM: Integrated Large Tabular Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bonet, David, Cara, Marçal Comajoan, Calafell, Alvaro, Montserrat, Daniel Mas, Ioannidis, Alexander G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911276855197696
author Bonet, David
Cara, Marçal Comajoan
Calafell, Alvaro
Montserrat, Daniel Mas
Ioannidis, Alexander G.
author_facet Bonet, David
Cara, Marçal Comajoan
Calafell, Alvaro
Montserrat, Daniel Mas
Ioannidis, Alexander G.
contents Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a default choice in practice. We present iLTM, an integrated Large Tabular Model that unifies tree-derived embeddings, dimensionality-agnostic representations, a meta-trained hypernetwork, multilayer perceptrons (MLPs), and retrieval within a single architecture. Pretrained on more than 1,800 heterogeneous classification datasets, iLTM achieves consistently superior performance across tabular classification and regression tasks, from small datasets to large and high-dimensional tasks. After light fine-tuning, the meta-trained hypernetwork transfers to regression targets, matching or surpassing strong baselines. Extensive experiments show that iLTM outperforms well-tuned GBDTs and leading deep tabular models while requiring less task-specific tuning. By bridging the gap between tree-based and neural methods, iLTM offers a new framework for tabular foundation models for robust, adaptable, and scalable tabular learning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15941
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle iLTM: Integrated Large Tabular Model
Bonet, David
Cara, Marçal Comajoan
Calafell, Alvaro
Montserrat, Daniel Mas
Ioannidis, Alexander G.
Machine Learning
Artificial Intelligence
68T05 (Primary) 68T07, 68T10 (Secondary)
I.2.6; I.5.1; H.2.8
Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a default choice in practice. We present iLTM, an integrated Large Tabular Model that unifies tree-derived embeddings, dimensionality-agnostic representations, a meta-trained hypernetwork, multilayer perceptrons (MLPs), and retrieval within a single architecture. Pretrained on more than 1,800 heterogeneous classification datasets, iLTM achieves consistently superior performance across tabular classification and regression tasks, from small datasets to large and high-dimensional tasks. After light fine-tuning, the meta-trained hypernetwork transfers to regression targets, matching or surpassing strong baselines. Extensive experiments show that iLTM outperforms well-tuned GBDTs and leading deep tabular models while requiring less task-specific tuning. By bridging the gap between tree-based and neural methods, iLTM offers a new framework for tabular foundation models for robust, adaptable, and scalable tabular learning.
title iLTM: Integrated Large Tabular Model
topic Machine Learning
Artificial Intelligence
68T05 (Primary) 68T07, 68T10 (Secondary)
I.2.6; I.5.1; H.2.8
url https://arxiv.org/abs/2511.15941