Deep Learning Through the Lens of Classical SQL

Abstract

In-database machine learning has been very popular, almost being a cliche. However, can we do it the other way around? In this work, we say “yes” by applying plain old SQL to Deep Learning (DL), in a sense, hypothetically implementing deep learning algorithms with SQL. Most deep learning frameworks, as well as generic machine learning ones, share a de facto standard of multidimensional array operations, underneath fancier infrastructure such as automatic differentiation. As SQL tables can be regarded as generalizations of (multi-dimensional) arrays, we have found a way to express common deep learning operations in SQL, encouraging a different way of thinking and thus potentially novel models. In particular, one of the latest trend in deep learning was the introduction of sparsity in the name of Graph Convolutional Networks (GCNs), whereas we take sparsity almost for granted in the database world. As both databases and machine learning involve transformation of datasets, we hope this work can inspire further works utilizing the large body of existing wisdom, algorithms and technologies in the database field to advance the state-of-the-art in machine learning, rather than merely integrating machine learning into databases.