Position: Why Tabular Foundation Models Should Be a Research Priority

Authors: Boris Van Breugel, Mihaela Van Der Schaar

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this position piece we aim to shift the ML research community s priorities ever so slightly to a different modality: tabular data. Tabular data is the dominant modality in many fields, yet it is given hardly any research attention and significantly lags behind in terms of scale and power. We believe the time is now to start developing tabular foundation models, or what we coin a Large Tabular Model (LTM). LTMs could revolutionise the way science and ML use tabular data: not as single datasets that are analyzed in a vacuum, but contextualized with respect to related datasets. The potential impact is far-reaching: from few-shot tabular models to automating data science; from out-of-distribution synthetic data to empowering multidisciplinary scientific discovery. We intend to excite reflections on the modalities we study, and convince some researchers to study large tabular models.
Researcher Affiliation Academia Boris van Breugel 1 Mihaela van der Schaar 1 2 1Department of Applied Mathematics and Theoretical Physics, University of Cambridge, UK 2Alan Turing Institute, London, UK. Correspondence to: Boris van Breugel <bv292@cam.ac.uk>.
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No This is a position paper discussing future research directions and does not present a specific methodology with associated code.
Open Datasets No This paper is a position piece and does not conduct experiments requiring dataset access information.
Dataset Splits No This paper is a position piece and does not conduct experiments that would require dataset splits.
Hardware Specification No This paper is a position piece and does not describe experiments that would require hardware specifications.
Software Dependencies No This paper is a position piece and does not describe experiments that would require software dependencies.
Experiment Setup No This paper is a position piece and does not describe experiments or their setup.