# Cross-Table Pretraining towards a Universal Function Space for Heterogeneous Tabular Data

arXiv: https://arxiv.org/abs/2406.00281 · HTML: https://mlsanity.com/paper/2406.00281/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://mlsanity.com/paper/1810.11921/) (2018)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [XTab: Cross-table Pretraining for Tabular Transformers](https://mlsanity.com/paper/2305.06090/) (2023)
- [Transfer Learning with Deep Tabular Models](https://mlsanity.com/paper/2206.15306/) (2022)
- [T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction](https://mlsanity.com/paper/2211.16887/) (2022)
- [Unlocking the Transferability of Tokens in Deep Models for Tabular Data](https://mlsanity.com/paper/2310.15149/) (2023)
- [Adapted tree boosting for Transfer Learning](https://mlsanity.com/paper/2002.11982/) (2020)

## Built on by (most cited first, 2 of 2)

- [Table Foundation Models: on knowledge pre-training for tabular learning](https://mlsanity.com/paper/2505.14415/) (2025)
- [Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training](https://mlsanity.com/paper/2506.10952/) (2025)

## Abstract (arXiv)

Tabular data from different tables exhibit significant diversity due to varied definitions and types of features, as well as complex inter-feature and feature-target relationships. Cross-dataset pretraining, which learns reusable patterns from upstream data to support downstream tasks, have shown notable success in various fields. Yet, when applied to tabular data prediction, this paradigm faces challenges due to the limited reusable patterns among diverse tabular datasets (tables) and the general scarcity of tabular data available for fine-tuning. In this study, we fill this gap by introducing a cross-table pretrained Transformer, XTFormer, for versatile downstream tabular prediction tasks. Our methodology insight is pretraining XTFormer to establish a "meta-function" space that encompasses all potential feature-target mappings. In pre-training, a variety of potential mappings are extracted from pre-training tabular datasets and are embedded into the "meta-function" space, and suited mappings are extracted from the "meta-function" space for downstream tasks by a specified coordinate positioning approach. Experiments show that, in 190 downstream tabular prediction tasks, our cross-table pretrained XTFormer wins both XGBoost and Catboost on 137 (72%) tasks, and surpasses representative deep learning models FT-Transformer and the tabular pre-training approach XTab on 144 (76%) and 162 (85%) tasks.