Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks

ArXi:2605.16085v1 Announce Type: cross Relational databases much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches flatten databases into single tables via manual feature engineering, discarding relational context. Relational deep learning (RDL) addresses this by modeling databases as relational entity graphs (REGs) for graph neural networks (GNNs), but remains task- and database-specific.