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

翻译：关系预测任务是许多现实应用中的基础问题，这类数据通常以关系数据库（RDBs）形式自然存储。关系深度学习（RDL）通过将关系数据库建模为图并应用图神经网络（GNNs）进行端到端学习来解决该问题。然而，在关系数据库的图构建中，全分辨率特性通常被视为设计原则以保留关系语义，这导致现有方法大多依赖固定图结构。本文提出FROG框架——一种面向RDL的全分辨率可优化图结构学习框架，将关系结构学习形式化为可学习的表角色建模问题，使表能够作为节点和边参与消息传递。我们进一步设计角色驱动消息传递机制以捕获关系语义，实现图结构与GNN表示的联合优化。为确保语义一致性，我们引入函数依赖约束对表级和实体级表示进行正则化。大量实验表明，本方法优于现有方法，并揭示了表角色对下游任务的影响机制，为RDL的图构建提供了新见解。