arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.17673cs.LG
收藏

LaTable:迈向大型表格模型

LaTable: Towards Large Tabular Models

University of Cambridge(剑桥大学)

Boris van Breugel, Jonathan Crabbé, Rob Davis, Mihaela van der Schaar

AI总结:

本文提出LaTable,一种能在异构表格数据集上跨域训练的表格扩散模型,解决了分布内生成优于基线且少样本微调效果更佳的问题,并探讨了其零样本性能对构建表格基础模型的启示。

摘要:

表格数据是最普遍的模态之一,但关于表格生成基础模型的文献远远落后于文本和视觉领域。构建此类模型十分困难,原因在于不同表格数据集的异构特征空间、表格元数据(如数据集描述和特征表头),以及表格缺乏先验知识(如特征顺序)。在本研究中,我们提出了LaTable:一种新颖的表格扩散模型,它解决了这些挑战,并能在不同数据集上进行训练。通过大量实验,我们发现LaTable在分布内生成上优于基线,并且微调LaTable能用更少样本更好地生成分布外数据集。另一方面,我们探讨了LaTable较差的零样本性能,以及它可能为构建具有更优零样本和少样本生成能力的表格生成基础模型带来的启示。

英文摘要:

Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of different tabular datasets, tabular metadata (e.g. dataset description and feature headers), and tables lacking prior knowledge (e.g. feature order). In this work we propose LaTable: a novel tabular diffusion model that addresses these challenges and can be trained across different datasets. Through extensive experiments we find that LaTable outperforms baselines on in-distribution generation, and that finetuning LaTable can generate out-of-distribution datasets better with fewer samples. On the other hand, we explore the poor zero-shot performance of LaTable, and what it may teach us about building generative tabular foundation models with better zero- and few-shot generation capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑