TablEye：透过图像之镜观察小型表格
TablEye: Seeing small Tables through the Lens of Images
AI总结：
TablEye通过将表格数据转换为图像以利用图像域先验知识，在少样本表格学习中超越TabLLM和STUNT，显著提升AUC和准确率。
摘要：
少样本表格学习的探索变得势在必行。表格数据是一种能够捕捉多样信息的多功能表示形式，但它并非没有局限性，包括数据属性和模型规模方面的限制。为大量表格数据打标签可能十分困难，而且可能无法捕捉每一个重要特征。然而，少样本表格学习仍然相对未被探索，主要原因在于独立数据集之间共享信息的稀缺性，以及表格数据中边界定义所固有的模糊性。据我们所知，目前尚未开发出任何有意义且不受限制的少样本表格学习技术，能够不对数据集施加约束。在本文中，我们提出了一个名为TablEye的创新框架，旨在通过采用领域变换来克服为表格数据形成先验知识的限制。该框架通过生成表格图像来促进领域变换，从而有效保留原始表格数据的内在语义。该方法利用经过严格测试的少样本学习算法和嵌入函数来获取并应用先验知识。利用共享数据领域，我们能够使用最初从图像领域学习到的先验知识。具体而言，TablEye在4-shot任务中超越了TabLLM，AUC最高提升0.11，并在1-shot设置下优于STUNT，平均准确率领先3.17%。
英文摘要：
The exploration of few-shot tabular learning becomes imperative. Tabular data is a versatile representation that captures diverse information, yet it is not exempt from limitations, property of data and model size. Labeling extensive tabular data can be challenging, and it may not be feasible to capture every important feature. Few-shot tabular learning, however, remains relatively unexplored, primarily due to scarcity of shared information among independent datasets and the inherent ambiguity in defining boundaries within tabular data. To the best of our knowledge, no meaningful and unrestricted few-shot tabular learning techniques have been developed without imposing constraints on the dataset. In this paper, we propose an innovative framework called TablEye, which aims to overcome the limit of forming prior knowledge for tabular data by adopting domain transformation. It facilitates domain transformation by generating tabular images, which effectively conserve the intrinsic semantics of the original tabular data. This approach harnesses rigorously tested few-shot learning algorithms and embedding functions to acquire and apply prior knowledge. Leveraging shared data domains allows us to utilize this prior knowledge, originally learned from the image domain. Specifically, TablEye demonstrated a superior performance by outstripping the TabLLM in a 4-shot task with a maximum 0.11 AUC and a STUNT in a 1- shot setting, where it led on average by 3.17% accuracy.
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。
