构建首个系统性评估关系深度学习的框架，揭示模型性能与数据库特征的关系。
REDELEX: A Framework for Relational Deep Learning Exploration
- 将关系数据库建模为图结构，用图神经网络统一评估不同模型。
- 在70多个数据库上验证，发现模型复杂度和数据规模是关键影响因素。
- 开源完整数据集与评估框架，适合研究关系学习与数据库应用者。
关系数据库（RDB）被视为存储结构化信息的黄金标准，基于此类数据的预测任务具有重要应用前景。近年来，关系深度学习（RDL）作为一种新范式，将关系数据库视为图结构，使多种图神经网络架构可有效应用于相关任务。然而由于其新颖性，目前尚缺乏对不同RDL模型性能与底层数据库特征之间关系的系统分析。本文提出REDELEX——一个全面的探索框架，用于在超过70个多样化关系数据库上评估不同复杂度的RDL模型，并向社区公开这些数据。在与经典方法的基准对比中，我们确认了RDL的普遍优越性，并揭示了影响性能的主要因素，包括模型复杂度、数据库规模及其结构特性。
原文摘要 · Abstract (English)
Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning (RDL) has emerged as a novel paradigm wherein RDBs are conceptualized as graph structures, enabling the application of various graph neural architectures to effectively address these tasks. However, given its novelty, there is a lack of analysis into the relationships between the performance of various RDL models and the characteristics of the underlying RDBs. In this study, we present REDELEX$-$a comprehensive exploration framework for evaluating RDL models of varying complexity on the most diverse collection of over 70 RDBs, which we make available to the community. Benchmarked alongside key representatives of classic methods, we confirm the generally superior performance of RDL while providing insights into the main factors shaping performance, including model complexity, database sizes and their structural properties.
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。