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

2026-05-20

AI Summary

This work proposes FROG, a novel framework that addresses the limitations of existing relational deep learning approaches, which typically rely on fixed graph structures and struggle to adaptively optimize for improved predictive performance. FROG introduces table roles—derived from relational database schemas—into graph structure learning, constructing a learnable, full-resolution graph where tables can function as either nodes or edges in message passing. By integrating a role-driven message-passing mechanism with functional dependency constraints, FROG jointly optimizes both graph topology and GNN representations while preserving semantic consistency. Extensive experiments demonstrate that FROG significantly outperforms state-of-the-art models across multiple relational prediction tasks, highlighting the critical influence of table roles on downstream performance and establishing a new paradigm for graph construction in relational deep learning.

Abstract

Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored 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. In this paper, we propose FROG, a Full-Resolution and Optimizable Graph Structure Learning} framework for RDL that formulates relational structure learning as a learnable table role modeling problem, allowing tables to contribute as nodes and edges in message passing. We further design role-driven message passing mechanisms to capture relational semantics, enabling joint optimization of graph structure and GNN representations. To ensure semantic consistency, we introduce functional dependency constraints that regularize representations across table and entity levels. Extensive experiments demonstrate that our method outperforms existing approaches and reveal how table roles impact downstream tasks, offering new insights into graph construction for RDL

Problem

• Relational Deep Learning
• Graph Structure Learning
• Relational Databases
• Fixed Schema Graphs
• Full-Resolution Graph

Innovation

• Graph Structure Learning
• Relational Deep Learning
• Table Role Modeling
• Message Passing
• Functional Dependency Constraints