发表机构
University of Kentucky; Institute for Biomedical Informatics（肯塔基大学; 生物医学信息学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出TabNSM框架，通过自适应稀疏交互模块、多阶段回归头等组件，在9个真实回归基准上实现高维表格回归的优性能与可扩展性。
AI 中文摘要
大规模高维表格回归仍具挑战性：树模型鲁棒但缺乏端到端表示学习，而深度学习模型虽支持灵活特征学习，但常带来高昂的交互建模成本，且对噪声或冗余特征敏感。我们提出TabNSM，一个可扩展的回归框架，扩展了我们早期的稀疏注意力与混合器架构。其核心是自适应稀疏交互模块（ASIM），整合前景特征发现、稀疏局部交互编码及特征-标记混合，在固定稀疏配置下实现近线性复杂度。针对回归任务，TabNSM引入三个互补组件：用于渐进式预测优化的多阶段回归头；GridLoss，一种感知序数的软分箱目标，将目标结构融入表示学习；以及RISE（基于误差的重加权实例采样），一种基于损失分位数箱的感知难度采样策略。在9个真实回归基准测试中，TabNSM展现出强劲的预测性能与实用的可扩展性，在高维和异构数据集上尤其取得稳定提升。这些结果表明，选择性交互建模、结构化回归监督与感知难度采样，为深度表格回归提供了一种有效且可扩展的方法。
英文摘要
Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while deep models enable flexible feature learning but often incur costly interaction modeling and sensitivity to noisy or redundant features. We propose TabNSM, a scalable regression framework that extends our earlier sparse-attention and mixer architectures. At its core, the Adaptive Sparse Interaction Module (ASIM) integrates foreground feature discovery, sparse local interaction encoding, and Feature-Token Mixing, providing near-linear complexity under fixed sparse configurations. For regression, TabNSM introduces three complementary components: a Multi-Stage Regression Head for progressive prediction refinement; GridLoss, an ordinal-aware soft-binning objective that incorporates target structure into representation learning; and RISE (Reweighted Instance Sampling by Error), a difficulty-aware sampling strategy based on loss-quantile bins. Across nine real-world regression benchmarks, TabNSM delivers strong predictive performance and practical scalability, with particularly consistent gains on high-dimensional and heterogeneous datasets. These results demonstrate that selective interaction modeling, structured regression supervision, and difficulty-aware sampling provide an effective and scalable approach to deep tabular regression.
