发表机构
University of Texas at Arlington（德克萨斯大学阿灵顿分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MetaSieve是一种基于SQL的元路径选择层，可剪枝关系深度学习中无信息的元路径，在多种GNN架构上能大幅缩短训练时间并维持或提升准确性。
AI 中文摘要
关系深度学习（RDL）是针对多表关系数据库进行机器学习的有效方法。在RDL中，数据库被建模为图，其中每一行对应一个节点，每个外键关系对应一条边，图神经网络（GNN）在该图上进行训练。训练GNN需要对训练集中的每个种子节点采样其周围的子图，训练成本在很大程度上取决于这些子图的规模。本文旨在利用关系数据库系统的连接和聚合能力来减小子图规模。我们观察到，采样得到的子图是通过遵循由外键链接组成的元路径获得的，且许多此类元路径可以在不损失准确性的情况下被剪枝。我们提出了MetaSieve，一种元路径选择层，用于确定保留哪些元路径、剪枝哪些元路径。对于每个候选元路径扩展，MetaSieve通过SQL连接和聚合查询计算统计量，并基于一种新颖的评分函数评估该扩展，该评分函数更倾向于轻量级但信息丰富的候选元路径。评分低于阈值的元路径被视为无信息并被剪枝。MetaSieve中的元路径选择是轻量级的，因为它仅依赖数据库统计量和任务标签，且与GNN参数无关，因此可与用于分类和回归的多种GNN架构集成。我们在RelBench基准上使用多个GNN骨干进行的评估表明，MetaSieve能持续大幅减少每轮训练时间，同时保持且常提升准确性。
英文摘要
Relational Deep Learning (RDL) is an effective approach to machine learning over multi-table relational databases. In RDL, a database is modeled as a graph in which each row is a node and each foreign-key relation is an edge, and a graph neural network (GNN) is trained on this graph. Training a GNN requires sampling a subgraph around every seed node in the training set, and the cost of training is largely determined by the size of these subgraphs. This paper aims to reduce subgraph size by leveraging the join and aggregation capabilities of relational database systems. We observe that sampled subgraphs are obtained by following metapaths composed of foreign-key links, and that many of these metapaths can be pruned without loss of accuracy. We present MetaSieve, a metapath selection layer that determines which metapaths to retain and which to prune. For each candidate metapath extension, MetaSieve computes statistics via SQL join and aggregation queries and evaluates the extension based on a novel scoring function that prefers lightweight but informative candidates. Metapaths whose scores fall below a threshold are deemed uninformative and pruned. Metapath selection in MetaSieve is lightweight since it relies only on database statistics and task labels, and it is independent of GNN parameters, so it integrates with diverse GNN architectures for classification and regression. Our evaluation on the RelBench benchmark with multiple GNN backbones shows that MetaSieve consistently reduces per-epoch training time by large margins while maintaining and often improving accuracy.
