Tabular data is prevalent across various machine learning domains. Yet, the inherent heterogeneities in attribute and class spaces across different tabular datasets hinder the effective sharing of knowledge, limiting a tabular model to benefit from other datasets. In this paper, we propose Tabular data Pre-Training via Meta-representation (TabPTM), which allows one tabular model pre-training on a set of heterogeneous datasets. Then, this pre-trained model can be directly applied to unseen datasets that have diverse attributes and classes without additional training. Specifically, TabPTM represents an instance through its distance to a fixed number of prototypes, thereby standardizing heterogeneous tabular datasets. A deep neural network is then trained to associate these meta-representations with dataset-specific classification confidences, endowing TabPTM with the ability of training-free generalization. Experiments validate that TabPTM achieves promising performance in new datasets, even under few-shot scenarios.
View on arXiv@article{ye2025_2311.00055,
title={ Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective },
author={ Han-Jia Ye and Qi-Le Zhou and Huai-Hong Yin and De-Chuan Zhan and Wei-Lun Chao },
journal={arXiv preprint arXiv:2311.00055},
year={ 2025 }
}