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.

翻译：我们研究了如何在不重新训练大型骨干网络的情况下，使小型表格基础模型能够有效处理高维低样本量（HDLSS）表格预测任务。本文引入图引导排序与局部精化（GO-LR）方法，证明了其与加权最小线性排列的等价性，并将实用求解器解释为一种类旅行商路径的替代方案。我们提出了基于GO-LR的GOTabPFN模型以及神经启发的子单元压缩（NSC）模块，该模块可将局部相邻的有序特征池化为元特征，从而生成紧致表示，使TabPFN风格的预测在HDLSS场景下具备实用性。在多个表格基准测试中，GOTabPFN在严格词元预算约束下提升了稳定性和精度。