Tabular foundation models for non-tabular tasks

📅 2026-08-23
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
研究使用TabPFN v3模型解决非表格数据分类问题,将图像和文本数据转化为表格形式进行处理,无需额外训练即可达到与专用模型相近的准确率。
📝 Abstract
Tabular foundation models (TFMs) have recently emerged as a promising paradigm for machine learning on tabular data, offering the ability to generalize across datasets without task-specific training. Since many machine learning datasets can be represented as tables, this raises the question: does TFM capability extend beyond tasks traditionally regarded as tabular? We address this question by using TabPFN v3 on three non-tabular classification problems: handwritten digit recognition on MNIST, language identification of French and German words, and image classification on Tiny ImageNet. In each case, the original data are represented as rows of a table and classification is formulated as prediction of a missing label. We evaluate performance as a function of the number of context samples provided to the pretrained model, with no additional training or fine-tuning. Despite having no explicit access to the spatial or sequential structure characterizing the data, TabPFN v3 in some cases achieves accuracies comparable with that of models or methods geared specifically toward the corresponding tasks.
Problem

Research questions and friction points this paper is trying to address.

Tabular Foundation Models
non-tabular tasks
classification
Innovation

Methods, ideas, or system contributions that make the work stand out.

tabular foundation models
non-tabular tasks
generalization
classification
context samples
G
Goran Nakerst
Institut für Theoretische Physik, Technische Universität Dresden, 01062 Dresden, Germany
John Brennan
John Brennan
Department of Physics, Maynooth University, Ireland
W
Wouter Beugeling
Physikalisches Institut (EP3) and Institute for Topological Insulators, Universität Würzburg, Am Hubland, 97074 Würzburg, Germany
Masudul Haque
Masudul Haque
Institut für Theoretische Physik, Technische Universität Dresden, 01062 Dresden, Germany