用表格模型处理非表格任务，零训练也能达到不错效果。
Tabular foundation models for non-tabular tasks
- 将图像、文本等数据转为表格形式，用预训练表格模型直接预测标签。
- 在MNIST等任务上，仅用少量样例即达90%以上准确率。
- 无需微调，适合快速原型验证和跨模态任务探索。
表格基础模型（TFMs）最近成为表格式数据机器学习的有前景范式，具备在不进行特定任务训练的情况下跨数据集泛化的能力。由于许多机器学习数据集可表示为表格，这引出一个问题：TFM能力是否能扩展到传统意义上的非表格任务？我们通过在三个非表格分类问题上使用TabPFN v3来回答此问题：在MNIST上的手写数字识别、法语与德语单词的语言识别，以及在Tiny ImageNet上的图像分类。每个任务中，原始数据被表示为表格的行，分类被建模为对缺失标签的预测。我们在不进行任何额外训练或微调的前提下，评估了模型性能随上下文样本数量的变化。尽管模型没有显式访问数据的空间或序列结构，但在某些情况下，TabPFN v3的表现已接近专门为此类任务设计的模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。