用可学习激活函数的KAN网络提升表格数据建模效果
TabKAN: Advancing Tabular Data Analysis using Kolmogorov-Arnold Network
- 基于可学习激活函数的KAN架构，增强模型可解释性
- 在多个公开数据集上超越传统模型和Transformer
- 适合需要高可解释性的表格数据分析场景
表格数据建模面临异构特征类型、缺失值和复杂特征交互等挑战。尽管梯度提升等传统机器学习方法常优于深度学习，但新型神经网络架构展现出潜力。本文提出TabKAN，一种基于科尔莫戈罗夫-阿诺德网络（KAN）的表格数据分析框架。与传统深度学习模型不同，KAN在边节点使用可学习激活函数，提升了可解释性和训练效率。TabKAN采用模块化KAN结构专为表格分析设计，并提出跨领域知识迁移的微调框架。此外，开发了模型特定的可解释性方法，减少对事后解释的依赖。在多个公开数据集上的实验表明，TabKAN在监督学习任务中表现优异，在二分类和多分类任务中显著优于经典模型与基于Transformer的方法。结果表明，基于KAN的架构有望弥合传统机器学习与深度学习在结构化数据上的差距。
原文摘要 · Abstract (English)
Tabular data analysis presents unique challenges that arise from heterogeneous feature types, missing values, and complex feature interactions. While traditional machine learning methods like gradient boosting often outperform deep learning, recent advancements in neural architectures offer promising alternatives. In this study, we introduce TabKAN, a novel framework for tabular data modeling based on Kolmogorov-Arnold Networks (KANs). Unlike conventional deep learning models, KANs use learnable activation functions on edges, which improves both interpretability and training efficiency. TabKAN incorporates modular KAN-based architectures designed for tabular analysis and proposes a transfer learning framework for knowledge transfer across domains. Furthermore, we develop a model-specific interpretability approach that reduces reliance on post hoc explanations. Extensive experiments on public datasets show that TabKAN achieves superior performance in supervised learning and significantly outperforms classical and Transformer-based models in binary and multi-class classification. The results demonstrate the potential of KAN-based architectures to bridge the gap between traditional machine learning and deep learning for structured data.
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。