Why Tabular Foundation Models Should Be a Research Priority
This position piece aims to shift ML research priorities toward tabular foundation models, which could impact fields reliant on tabular data, though it is incremental as it builds on existing foundation model concepts.
The authors argue that tabular data, despite being dominant in many fields, receives insufficient research attention compared to text and image modalities, and propose developing Large Tabular Models (LTMs) to revolutionize its use by enabling contextualization across datasets.
Recent text and image foundation models are incredibly impressive, and these models are attracting an ever-increasing portion of research resources. 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.