MetaRTL：元路径注意力增强的关系表学习
MetaRTL: Meta-path Attention Enhanced Relational Table Learning
- Shanghai Jiao Tong University（上海交通大学）
- Shanghai Key Laboratory of Integrated Administration Technologies for Information Security（上海市信息安全综合管理技术重点实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MetaRTL提出两阶段框架，通过轻量预训练和非参数元路径聚合替代深度GNN，在10个数据集24项任务上实现高效且富有表现力的关系表学习。
AI中文摘要：
随着关系数据库的广泛使用，关系表学习日益受到关注。现有方法通常依赖深度图神经网络（GNN）或异构图神经网络（HGNN）堆叠，导致计算成本高，且在大型真实世界数据库上性能有限。我们提出MetaRTL，一个两阶段框架，用于可扩展且富有表现力的关系表学习。在第一阶段，MetaRTL通过轻量级预训练获得初始表嵌入。在第二阶段，它执行非参数消息传递以推导元路径特征，然后由注意力模块MetaAttn进行聚合。通过将计算从深度消息传递转移到高效的元路径聚合，MetaRTL在保持高效率的同时捕获了丰富的关系语义。在24个任务上的10个真实世界数据集上的实验证明了所提方法的有效性。
英文摘要：
Relational table learning has gained increasing attention with the widespread use of relational databases. Existing methods typically rely on deep GNN or HGNN stacks, leading to high computational costs and limited performance on large real-world databases. We propose MetaRTL, a two-stage framework for scalable and expressive relational table learning. In the first stage, MetaRTL obtains initial table embeddings via lightweight pre-training. In the second stage, it performs non-parametric message passing to derive meta-path features, which are then aggregated by an attention module, MetaAttn. By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency. Experiments on 10 real-world datasets across 24 tasks demonstrate the effectiveness of the proposed method.
