让关系数据库图结构可学习，提升预测性能
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning
- 把表的角色当作可优化节点和边，动态构建图结构
- 在多个数据集上超越现有方法，最高提升7.2%准确率
- 适合做关系型数据建模的研究者与工程师
关系预测在众多实际应用中至关重要，数据通常存储于关系型数据库（RDBs）。关系深度学习（RDL）将RDBs建模为图，并使用图神经网络（GNN）进行端到端学习。然而，当前多数方法采用固定图结构以保持全分辨率属性，从而限制了模型灵活性。本文提出FROG框架，将关系结构学习建模为可学习的表角色问题，使表可作为消息传递中的节点和边。设计角色驱动的消息传递机制以捕捉关系语义，实现图结构与GNN表示的联合优化。通过函数依赖约束确保表级与实体级表示的一致性。大量实验表明，该方法优于现有方法，并揭示表角色对下游任务的影响，为RDL中的图构建提供了新视角。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。