RelGNN提升关系数据库图学习，通过原子路径增强消息传递效率
RelGNN: Composite Message Passing for Relational Deep Learning
- 设计原子路径实现源目标节点直接单跳交互
- 在30个真实任务上最高提升25%性能
- 适合处理多对多关系的复杂关系数据建模
关系数据库上的预测任务在电商、医疗和社交媒体等实际应用中至关重要。为有效应对这些任务，关系深度学习（RDL）将关系数据编码为图结构，使图神经网络（GNN）能够利用关系结构提升预测效果。然而，现有RDL方法常忽视从关系数据库构建的图的固有结构特性，导致建模效率低下，尤其在处理多对多关系时表现不佳。本文提出RelGNN，一种专为关系数据库图结构设计的新GNN框架。其核心是引入原子路径——支持源节点与目标节点间直接单跳交互的简单路径。基于原子路径，RelGNN设计了新的复合消息传递与图注意力机制，减少冗余，突出关键信号，提升预测准确性。RelGNN在Relbench（Fey et al., 2024）提供的30个多样化真实任务上进行评估，多数任务达到当前最优性能，最高提升达25%。代码已公开于https://github.com/snap-stanford/RelGNN。
原文摘要 · Abstract (English)
Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational data as graphs, enabling Graph Neural Networks (GNNs) to exploit relational structures for improved predictions. However, existing RDL methods often overlook the intrinsic structural properties of the graphs built from relational databases, leading to modeling inefficiencies, particularly in handling many-to-many relationships. Here we introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases. At the core of our approach is the introduction of atomic routes, which are simple paths that enable direct single-hop interactions between the source and destination nodes. Building upon these atomic routes, RelGNN designs new composite message passing and graph attention mechanisms that reduce redundancy, highlight key signals, and enhance predictive accuracy. RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority of tasks, with improvements of up to 25%. Code is available at https://github.com/snap-stanford/RelGNN.
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。