动态重排特征顺序，提升高维表格数据的深度学习效果
DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data
- 通过神经重连机制动态调整特征顺序，适应数据内在复杂性
- 在36个真实数据集上超越45个顶尖基线，高维数据提升显著
- 适合处理高维表格数据，尤其适用于序列敏感模型
高维表格数据缺乏自然特征顺序，限制了对排列敏感的深度学习模型的应用。我们提出DynaTab，一种受神经重连启发的动态特征排序架构。引入轻量级准则，量化数据内在复杂性以预测特征排列是否有益。DynaTab通过神经重连算法动态重排特征，并利用紧凑的、动态有序的组合结构——包括独立学习的位置嵌入、基于重要性的门控机制和掩码注意力层——处理特征，兼容任何序列敏感的主干网络。采用定制的动态特征排序（DFO）和分散损失端到端训练，在36个真实世界表格数据集上与45个先进基线对比，实现统计显著的性能提升，尤其在高维数据上表现突出。结果表明，DynaTab为高维表格深度学习提供了有力的新范式。
原文摘要 · Abstract (English)
High-dimensional tabular data lacks a natural feature order, limiting the applicability of permutation-sensitive deep learning models. We propose DynaTab, a dynamic feature ordering-enabled architecture inspired by neural rewiring. We introduce a lightweight criterion that predicts when feature permutation will benefit a dataset by quantifying its intrinsic complexity. DynaTab dynamically reorders features via a neural rewiring algorithm and processes them through a compact, dynamic order-aware combination of separate learned positional embedding, importance-based gating, and masked attention layers, compatible with any sequence-sensitive backbone. Trained end-to-end with bespoke dynamic feature ordering (DFO) and dispersion losses, DynaTab achieves statistically significant gains, particularly on high-dimensional datasets, where it is benchmarked against 45 state-of-the-art baselines across 36 different real-world tabular datasets. Our results position DynaTab as a compelling new paradigm for high-dimensional tabular deep learning.
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。