提出grables框架，让表格学习用上行间关系，提升时序/临床数据预测效果
Grables: Tabular Learning Beyond Independent Rows
- 设计grables接口，分离图构建与节点预测，明确表达能力来源
- 消息传递模型在交易和临床数据上显著优于独立行预测方法
- 适合处理依赖全局统计或关系结构的表格数据
表格学习仍以逐行独立预测为主，适用于i.i.d.基准但难以处理交易、时间序列和关系型表格中标签依赖其他行的问题。我们指出，行级预测排除了由全局计数、重叠和关系模式驱动的自然目标。为使‘利用结构’在不同架构中可量化，提出grables：一种模块化接口，将表格转为图的过程（构造器）与图上预测过程（节点预测器）分离，精准定位表达能力来源。在合成任务、交易数据及RelBench临床试验数据集上的实验验证了预期的分离效果：消息传递能捕捉行间依赖，而显式提取行间结构并输入强表格学习模型的混合方法持续带来性能提升。
原文摘要 · Abstract (English)
Tabular learning is still dominated by row-wise predictors that score each row independently, which fits i.i.d. benchmarks but fails on transactional, temporal, and relational tables where labels depend on other rows. We show that row-wise prediction rules out natural targets driven by global counts, overlaps, and relational patterns. To make "using structure" precise across architectures, we introduce grables: a modular interface that separates how a table is lifted to a graph (constructor) from how predictions are computed on that graph (node predictor), pinpointing where expressive power comes from. Experiments on synthetic tasks, transaction data, and a RelBench clinical-trials dataset confirm the predicted separations: message passing captures inter-row dependencies that row-local models miss, and hybrid approaches that explicitly extract inter-row structure and feed it to strong tabular learners yield consistent 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。