小模型也能高效处理高维低样本表格数据，关键在特征排序与压缩。
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
- 基于图引导的特征排序与局部优化，提升特征组织效率。
- 在有限令牌预算下，准确率与稳定性显著优于现有方法。
- 适合高维稀疏表格数据，尤其适用于资源受限场景。
我们研究如何使小型表格基础模型在高维低样本（HDLSS）表格预测任务中有效，而无需重新训练大型主干网络。提出图引导排序与局部优化（GO-LR），证明其等价于加权最小线性排列问题，并将实际求解器视为类似旅行商路径的近似方案。在此基础上构建GOTabPFN，引入神经启发式子单元压缩（NSC）机制，将局部相邻有序特征聚合为元特征，生成紧凑表示，使TabPFN类预测在HDLSS环境下可行。在多个表格基准测试中，GOTabPFN在严苛的令牌预算下实现了更高的稳定性和准确率。
原文摘要 · Abstract (English)
We investigate how to make small tabular foundation models effective for High-Dimensional, Low-Sample Size (HDLSS) tabular prediction without retraining large backbones. We introduce Graph-guided Ordering with Local Refinement (GO-LR), show its equivalence to weighted Minimum Linear Arrangement, and interpret the practical solver as a TSP-path-style surrogate. We propose GOTabPFN,which builds on GO-LR, and a Neuro-Inspired Subunit Compression (NSC) unit to pool locally adjacent ordered features into meta-features, yielding a compact representation that makes TabPFN-style prediction practical in HDLSS regimes. Across tabular benchmarks, GOTabPFN improves stability and accuracy under tight token budgets.
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。