Tabular Few-Shot Generalization Across Heterogeneous Feature Spaces
Abstract
Despite the prevalence of tabular datasets, few-shot learning remains under-explored within this domain. Existing few-shot methods are not directly applicable to tabular datasets due to varying column relationships, meanings, and permutational invariance. To address these challenges, we propose FLAT-a novel approach to tabular few-shot learning, encompassing knowledge sharing between datasets with heterogeneous feature spaces. Utilizing an encoder inspired by Dataset2Vec, FLAT learns low-dimensional embeddings of datasets and their individual columns, which facilitate knowledge transfer and generalization to previously unseen datasets. A decoder network parametrizes the predictive target network, implemented as a Graph Attention Network, to accommodate the heterogeneous nature of tabular datasets. Experiments on a diverse collection of 118 UCI datasets demonstrate FLAT's successful generalization to new tabular datasets and a considerable improvement over the baselines.
Cite
@article{arxiv.2311.10051,
title = {Tabular Few-Shot Generalization Across Heterogeneous Feature Spaces},
author = {Max Zhu and Katarzyna Kobalczyk and Andrija Petrovic and Mladen Nikolic and Mihaela van der Schaar and Boris Delibasic and Petro Lio},
journal= {arXiv preprint arXiv:2311.10051},
year = {2023}
}
Comments
Tabular learning, Deep learning, Few shot learning