发表机构
Ant Group（蚂蚁集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SCFF框架，通过支持排序特征路由和有界叶节点编码，将表格基础模型的二次方特征交互降为线性计算，在18数据集上以更低内存提升准确率，相对误差降低最高26.1%。
AI 中文摘要
表格基础模型面临特征侧的扩展困境：全宽度的两两特征交互计算量随列数呈二次方增长，而特征选择通过丢弃证据来节省内存。我们提出了支持编译的特征折叠（SCFF），这是一个无需训练的推理框架，在不改变冻结骨干网络的情况下解决了这一困境。SCFF将支持排序的特征路由到原生特征编码器的有界叶节点，对残余证据进行支持检查，并在单次上下文预测之前合并编码后的消息。由此，它将二次方的特征交互计算转化为线性于宽度的计算，并具有有界的局部工作集，无需集成预测或训练新参数。在固定的AMLB-29、TabZilla和TabArena快照的穷尽式18数据集宽表切片上，SCFF在所有六个评估骨干网络上提升了数据集宏平均准确率和负对数似然（NLL）。所有四次匹配宽度的比较在锁定折叠上均保持有利的95%数据集自助法置信区间，相对误差降低最高达26.1%。中位配对GPU内存节省为2.09倍至2.36倍，单独观测到的最大峰值之比达到34.3倍。在实测峰值内存上限下，SCFF利用节省的预算保留更多支持选择的证据，在TabICLv2和TabPFN-3的预先声明的宽Core分层上，相比最宽可行单叶节点，准确率分别提升4.06和3.72个百分点。
英文摘要
Wide tables offer tabular foundation models more evidence, but accessing it can exhaust their memory: full-width pairwise mixing grows quadratically with the number of columns, while feature selection makes inputs affordable by discarding evidence. We ask whether using more features requires interacting over all of them at once. We introduce Support-Compiled Feature Folding (SCFF), a training-free inference framework that encodes wide tables through bounded calls to a frozen backbone. SCFF organizes support-ranked features into a strong Core and a candidate Tail, folds them into narrow feature groups, and support-checks the Tail's added evidence before a single contextual prediction. This converts quadratic feature-interaction work into linear-in-width work with a bounded local working set, without ensembling predictions or training new parameters. On the exhaustive 18-dataset wide-table slice of fixed AMLB-29, TabZilla, and TabArena snapshots, SCFF improves dataset-macro accuracy and NLL on all six evaluated backbones. All four matched-width comparisons retain favorable 95% dataset-bootstrap intervals on locked folds, with relative error reductions up to 26.1%. Median paired GPU-memory savings are 2.09-2.36x, and the ratio of separately observed maximum peaks reaches 34.3x. Under a measured peak-memory ceiling, SCFF uses the saved budget to preserve more support-selected evidence, improving accuracy by 4.06 and 3.72 points over the widest feasible single leaf on predeclared wide-Core strata of TabICLv2 and TabPFN-3.
