Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

ArXi:2605.21475v1 Announce Type: new Relational prediction tasks are fundamental in many real-world applications, where data are naturally d in relational databases (RDBs). Relational Deep Learning (RDL) addresses this problem by modeling RDBs as graphs and applying graph neural networks (GNNs) for end-to-end learning. However, the full-resolution property is commonly adopted as a design principle in graph construction for RDBs to preserve relational semantics, which leads most existing methods to rely on fixed graph structures.