发表机构
Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出InRTL，一个统一框架，通过列感知编码器、Transformer自注意力与交叉注意力，以及线性化注意力和异构图神经网络，显式建模关系型表格的表内与表间交互，在24个真实任务上验证了有效性。
AI 中文摘要
关系型表格学习近来已成为建模通过主键-外键（PK-FK）关系连接的多张表格的重要研究方向。尽管近期取得了进展，但针对该任务量身定制的原则性建模框架仍未得到充分探索。在本文中，我们提出了表内-表间关系型表格学习（InRTL），这是一个统一框架，显式地建模关系型表格内部及跨表格的依赖关系。具体而言，InRTL形式化了两种互补的交互模式：表内交互，描述同一表格内行之间的关联；表间交互，描述通过主键-外键连接的表格间行之间的依赖关系。为建模这些依赖，我们开发了一个列感知的表编码器以生成初始行表示，随后分别采用基于Transformer的自注意力模块和交叉注意力模块进行表内学习和表间学习。为进一步提升可扩展性，InRTL引入了线性化注意力和异构图神经网络来简化自注意力和交叉注意力操作。在涵盖24个真实世界任务的十个数据集上的大量实验证明了我们方法的有效性。代码可在以下网址获取：此https URL。
英文摘要
Relational table learning has recently emerged as an important research direction for modeling multiple tables connected through primary key-foreign key (PK-FK) relationships. Despite recent advances, a principled modeling framework tailored to this task remains underexplored. In this paper, we propose Intra-Inter Relational Table Learning (InRTL), a unified framework that explicitly models dependencies both within and across relational tables. Specifically, InRTL formalizes two complementary interaction patterns: intra-table interactions, describing associations among rows within the same table, and inter-table interactions, describing dependencies between rows across PK-FK-linked tables. To model these dependencies, we develop a column-aware table encoder to generate initial row representations, followed by Transformer-based self-attention and cross-attention modules for intra-table and inter-table learning, respectively. To further improve scalability, InRTL incorporates linearized attention and heterogeneous graph neural networks to simplify the self-attention and cross-attention operations. Extensive experiments on ten datasets covering 24 real-world tasks demonstrate the effectiveness of our approach. Code is available at https://github.com/W1nterFloW/InRTL.
