Spotlight
in
Workshop: Table Representation Learning Workshop
TabPFGen – Tabular Data Generation with TabPFN
Jeremy (Junwei) Ma · Apoorv Dankar · George Stein · Guangwei Yu · Anthony Caterini
Keywords: [ in-context learning ] [ generative model ] [ tabular data ] [ tabpfn ] [ energy based model ]
Fri 15 Dec 6:30 a.m. PST — 3:30 p.m. PST
Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus devise a technique to turn TabPFN -- a highly performant transformer initially designed for in-context discriminative tabular tasks -- into an energy-based generative model, which we dub TabPFGen. This novel framework leverages the pre-trained TabPFN as part of the energy function and does not require any additional training or hyperparameter tuning, thus inheriting TabPFN's in-context learning capability. We can sample from TabPFGen analogously to other energy-based models. We demonstrate strong results on standard generative modelling tasks, including data augmentation, class-balancing, and imputation, unlocking a new frontier of tabular data generation.