Griffin是首个专为关系型数据库设计的通用基础模型，能统一处理多种任务。
Griffin: Towards a Graph-Centric Relational Database Foundation Model
- 采用统一编码器与解码器架构，结合交叉注意力和新型聚合模块。
- 在超1.5亿节点的跨域数据库图上表现优异，低数据场景下仍具强泛化能力。
- 适合需要通用数据库理解能力的研究者与开发者使用。
我们提出Griffin，首个专为关系型数据库（RDBs）设计的基础模型。不同于以往专注于单一任务的小规模模型，Griffin通过统一的数据编码器与任务解码器，实现对多样化任务的处理。通过引入交叉注意力模块与新型聚合机制，增强模型对复杂关系数据的捕捉能力。模型在单表及多表数据库数据集上进行预训练，采用先进编码器处理类别、数值与元数据特征，并结合创新组件如交叉注意力与增强的消息传递神经网络（MPNNs）。在来自多个领域、大规模、异构且具有时序特性的数据库图上（节点超过1.5亿），Griffin的表现优于或媲美独立训练的专用模型，在低数据条件下表现出色，展现出良好的迁移能力，预训练在新数据集与任务间呈现相似性与多样性，凸显其作为关系型数据库通用基础模型的巨大潜力。代码已公开于https://github.com/yanxwb/Griffin。
原文摘要 · Abstract (English)
We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Griffin unifies the data encoder and task decoder to handle diverse tasks. Additionally, we enhance the architecture by incorporating a cross-attention module and a novel aggregator. Griffin utilizes pretraining on both single-table and RDB datasets, employing advanced encoders for categorical, numerical, and metadata features, along with innovative components such as cross-attention modules and enhanced message-passing neural networks (MPNNs) to capture the complexities of relational data. Evaluated on large-scale, heterogeneous, and temporal graphs extracted from RDBs across various domains (spanning over 150 million nodes), Griffin demonstrates superior or comparable performance to individually trained models, excels in low-data scenarios, and shows strong transferability with similarity and diversity in pretraining across new datasets and tasks, highlighting its potential as a universally applicable foundation model for RDBs. Code available at https://github.com/yanxwb/Griffin.
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。