TabKANet:基于 Kolmogorov-Arnold Network 与 Transformer 的表格数据建模
TabKANet: Tabular Data Modeling with Kolmogorov-Arnold Network and Transformer
AI总结:
本文提出 TabKANet,通过基于 KAN 的数值嵌入模块与 Transformer 统一编码数值和类别特征,在多类表格任务上优于 NNs,并达到或超过 GBDTs。
摘要:
表格数据是现实场景中最常见的数据类型。在本研究中,我们提出用于表格数据建模的 TabKANet 模型,其针对从数值内容中学习时存在的瓶颈。我们构建了一个基于 Kolmogorov-Arnold Network(KAN)的数值嵌入模块,并在 Transformer 架构内统一了数值特征与类别特征的编码。在多个公开数据集的二分类、多分类和回归任务中,TabKANet 相比神经网络(NNs)表现出稳定且显著更优的性能。其性能可与梯度提升决策树模型(GBDTs)相媲美,甚至有所超越。我们的代码已在 GitHub 公开发布:https://github.com/AI-thpremed/TabKANet。
英文摘要:
Tabular data is the most common type of data in real-life scenarios. In this study, we propose the TabKANet model for tabular data modeling, which targets the bottlenecks in learning from numerical content. We constructed a Kolmogorov-Arnold Network (KAN) based Numerical Embedding Module and unified numerical and categorical features encoding within a Transformer architecture. TabKANet has demonstrated stable and significantly superior performance compared to Neural Networks (NNs) across multiple public datasets in binary classification, multi-class classification, and regression tasks. Its performance is comparable to or surpasses that of Gradient Boosted Decision Tree models (GBDTs). Our code is publicly available on GitHub: https://github.com/AI-thpremed/TabKANet.
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。