发表机构
Newcastle University（纽卡斯尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对表格分类中离散规则结构与欧氏空间DNN几何不匹配问题，提出HDE-Net，通过抽象特征为LDN并嵌入双曲空间，引入软决策路由机制和容量分配算法，在分类基准上取得最佳平均排名，优于其他方法。
AI 中文摘要
表格分类通常由局部条件触发规则而非平滑全局模式主导。然而，表格深度神经网络（DNN）通常基于有利于平滑变化和语义局部性的欧几里得表示构建。这种潜在的几何不匹配使得表格DNN难以有效表示表格分类背后的离散、规则划分结构。为解决此问题，我们提出HDE-Net，一种在双曲空间中实现分层决策建模的流形约束DNN。我们首先将异构特征抽象为统一的潜在决策节点（LDN）并嵌入庞加莱球中，形成类似树状结构推理的连续表示。对于数值特征，我们引入软决策路由机制以可微方式近似基于范围的局部规则，使LDN语义更接近分类特征。熵感知容量分配算法进一步调整每个数值特征的LDN数量以平衡表达能力和复杂性。在TALENT-tiny-core分类基准（30个数据集）上，HDE-Net实现了最佳平均排名，优于工业GBDT和近期表格DNN，同时保持高效率。
英文摘要
Tabular prediction is central to a wide range of real-world applications. Tabular data typically contain heterogeneous features as well as rich and complex relational information that can imply a latent structural manifold. Hyperbolic geometry can help capture complex structural relations in data. However, most existing tabular prediction models are constructed and optimized in Euclidean space. How to incorporate hyperbolic geometry into supervised tabular learning remains underexplored. We propose \textbf{HTNN}, a supervised hyperbolic manifold constrained tabular neural network for tabular prediction. HTNN consists of a hyperbolic feature-value representation layer for heterogeneous categorical and numerical features, followed by a conventional MLP predictor. HTNN employs a \emph{geometry-aware training} and \emph{geometry-free inference} optimization framework. The \emph{geometry-aware training} allows hyperbolic geometry to shape the latent representation learning of heterogeneous feature values. After training, the latent hyperbolic representations can be converted into ordinary Euclidean space for efficient \emph{geometry-free inference}. We conducted extensive experiments on the TALENT benchmark. HTNN ranks first among 36 methods on 200 classification datasets and third among 34 methods on 100 regression datasets. Experimental results show that the proposed hyperbolic manifold constrained tabular neural network is effective.
