As models are trained and deployed, developers need to be able to
systematically debug errors that emerge in the machine learning pipeline. We
present MDB, a debugging framework for interactively querying dataset
通过引入 ML Benchmark For Relational Databases (RDBench) 标准化基准测试,旨在促进多表关系数据库上可复现的机器学习研究,RDBench 为不同的机器学习领域提供多样的关系数据库数据集,使得从 XGBoost 到图神经网络等不同领域的 ML 方法可以进行有意义的比较和评估。