Modeling connections in linked database tables improves performance
InRTL: Effective Intra-Inter Interaction Learning for Relational Tables
Machine LearningArtificial Intelligence
Summary
Data in many real-world applications is stored in multiple tables linked by keys. The authors propose a new way to teach computers to understand both relationships inside one table and connections across different tables. They developed a system called InRTL that uses advanced techniques to capture these two kinds of patterns effectively. Experiments show this method helps computers learn from complex linked tables better than before.
What this means in practice
- •For database engineers: Improve querying and data integration by better modeling dependencies within and between database tables linked by keys.
- •For business intelligence teams: Enhance analytics workflows by using improved representations of relational data that capture complex table relationships automatically.
Authors
Weichen Li, Ken Zhong, Zheng Wang, Li Pan, Jianhua Li
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.