InRTL: Effective Intra-Inter Interaction Learning for Relational Tables

2026-09-11

AI Summary

本文提出InRTL框架，通过行内和跨表交互学习解决关系表建模问题，采用列感知编码器和注意力机制提升模型性能。

Abstract

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.

Problem

• Relational Table Learning
• PK-FK Relationships
• Intra-Table Interactions
• Inter-Table Interactions

Innovation

• Intra-Inter Relational Table Learning
• column-aware table encoder
• Transformer-based self-attention and cross-attention
• linearized attention
• heterogeneous graph neural networks