arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.20060cs.LGcs.AIcs.DB
收藏

RelBench:面向关系数据库深度学习的基准

RelBench: A Benchmark for Deep Learning on Relational Databases

Stanford University(斯坦福大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Joshua Robinson, Rishabh Ranjan, Weihua Hu, Kexin Huang, Jiaqi Han, Alejandro Dobles, Matthias Fey, Jan E. Lenssen, Yiwen Yuan, Zecheng Zhang, Xinwei He, Jure Leskovec

AI总结:

提出了 RelBench 基准,用于通过图神经网络解决关系数据库预测任务,并首次全面验证了关系深度学习(RDL)在减少人工特征工程的同时能学习到更优的预测模型。

摘要:

我们提出了 RelBench,这是一个用于通过图神经网络解决关系数据库预测任务的公开基准。RelBench 提供了涵盖不同领域和规模的数据库与任务,旨在成为未来研究的基础设施。我们利用 RelBench 对关系深度学习(RDL)(Fey et al., 2024) 进行了首次全面研究,该方法将图神经网络预测模型与从原始表格中提取初始实体级表示的(深度)表格模型相结合。端到端学习的 RDL 模型充分利用了主外键链接中编码的预测信号,标志着从手动特征工程结合表格模型这一主导范式的重大转变。为了将 RDL 与这一先前的黄金标准进行彻底比较,我们进行了一项深入的用户研究,由一位经验丰富的数据科学家为每个任务手动设计特征。在此研究中,RDL 学习到了更好的模型,同时将所需的人工工作量减少了一个数量级以上。这证明了深度学习在解决关系数据库预测任务方面的强大能力,开启了由 RelBench 支持的众多新研究机遇。

英文摘要:

We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational infrastructure for future research. We use RelBench to conduct the first comprehensive study of Relational Deep Learning (RDL) (Fey et al., 2024), which combines graph neural network predictive models with (deep) tabular models that extract initial entity-level representations from raw tables. End-to-end learned RDL models fully exploit the predictive signal encoded in primary-foreign key links, marking a significant shift away from the dominant paradigm of manual feature engineering combined with tabular models. To thoroughly evaluate RDL against this prior gold-standard, we conduct an in-depth user study where an experienced data scientist manually engineers features for each task. In this study, RDL learns better models whilst reducing human work needed by more than an order of magnitude. This demonstrates the power of deep learning for solving predictive tasks over relational databases, opening up many new research opportunities enabled by RelBench.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑