iLTM: Integrated Large Tabular Model
By: David Bonet , Marçal Comajoan Cara , Alvaro Calafell and more
Potential Business Impact:
Makes computers learn from data much better.
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.
Similar Papers
Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
Artificial Intelligence
Lets computers learn from small data sets.
MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML
Computation and Language
Teaches computers to learn from many examples.
TabGemma: Text-Based Tabular ICL via LLM using Continued Pretraining and Retrieval
Machine Learning (CS)
Helps computers understand and predict from mixed data.