用柯尔莫哥洛夫-阿诺德网络提升表格数据建模效果
TabKANet: Tabular Data Modeling with Kolmogorov-Arnold Network and Transformer
- 基于KAN构建数值特征嵌入模块，统一处理数值与类别特征
- 在多个公开数据集上性能优于传统神经网络，媲美甚至超过GBDT
- 适合需要高精度表格数据建模的科研与工业场景
表格数据是现实场景中最常见的数据类型。本文提出TabKANet模型，针对数值内容学习中的瓶颈问题，构建基于柯尔莫哥洛夫-阿诺德网络（KAN）的数值嵌入模块，并将数值与类别特征编码统一整合进Transformer架构。在二分类、多分类和回归任务中，TabKANet在多个公开数据集上表现出稳定且显著优于传统神经网络（NNs）的性能，其表现可与或超越梯度提升决策树模型（GBDTs）。代码已开源：https://github.com/AI-thpremed/TabKANet。
原文摘要 · Abstract (English)
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.
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。