FROG解决了RDL中固定图结构无法优化的问题，做关系数据库和图神经网络结合的研究者可以直接用这个框架提升模型效果，值得深入阅读。
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（GNN）进行端到端学习，但现有方法多依赖固定图结构，限制了表达能力。本文提出FROG框架，将关系结构学习转化为可学习的表角色建模问题，允许表作为节点和边参与消息传递，并设计角色驱动消息传递机制以捕捉关系语义。FROG还引入函数依赖约束，确保表与实体级别的表示一致性。实验表明，FROG在多个任务上超越现有方法，并揭示了表角色对下游任务的影响，为RDL的图构建提供了新见解。
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
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