将表格数据转为结构化图像表示，提升模型性能与鲁棒性
Table2Image: Lightweight Tabular Learning with Generated Proxy Representations and Reliability Diagnostics
- 用可学习的生成路径将表格转为结构化代理表示
- 在多个数据集上实现良好性能且模型更轻量
- 支持在噪声、错误标签等条件下评估可靠性
深度表格模型应兼顾预测性能、参数效率和对不完美学习信号的鲁棒性，但这些特性很少被共同考虑。我们提出Table2Image，一种基于可学习生成路径的轻量级表格学习模型，该路径将表格输入映射为中间结构化代理表示。我们还引入一种基于方差膨胀因子（VIF）初始化的变体，在训练初期降低高度共线特征的影响。在OpenML-CC18和TabZilla的数据集上，Table2Image实现了具有竞争力的干净预测性能，同时相比多个大规模神经基线模型更为紧凑。我们进一步提出一个统一的、受控的评估协议，涵盖三种不完美学习条件：无关输入、污染监督和不稳定捷径关联，结合基于性能的鲁棒性度量与实例级不稳定诊断，用于可靠性表征。Table2Image在性能、鲁棒性和紧凑性之间保持了良好平衡。受控消融实验表明，可学习的生成路径是性能提升的关键驱动因素。
原文摘要 · Abstract (English)
Deep tabular models should ideally balance predictive performance, parameter efficiency, and robustness to imperfect learning signals---properties that are rarely considered jointly. We present Table2Image, a lightweight tabular learning model built around a learned generation pathway that maps tabular inputs into intermediate, structured proxy representations. We additionally examine a variant with variance inflation factor (VIF)-informed initialization, which downweights highly collinear features at the start of training. Across datasets from OpenML-CC18 and TabZilla, Table2Image achieves competitive clean predictive performance while remaining compact relative to several large-scale neural baselines. We further introduce a unified, severity-controlled evaluation protocol under three imperfect learning conditions---irrelevant inputs, corrupted supervision, and unstable shortcut associations---that combines performance-based robustness measures with realization-level instability diagnostics for reliability characterization. Table2Image maintains a favorable balance of performance, robustness, and compactness. Controlled ablations indicate that the learned generation pathway is a key driver of the observed gains.
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。