SQL4NN: Validation and expressive querying of models as data

Any serious machine learning project will quickly produce a multitude of models learned from data. These models are then validated, tested in different ways, modified, retrained, and archived or deployed. This multitude of models also constitutes valuable data in itself. We may refer to such data as intensional, in contrast to what we already know as extensional data: training data, background data, data for validation, etc. Our point of view in this paper is that models are data too and should be managed using database technology, just like the extensional data. In particular, we should be able to query models. Indeed, many tasks that we usually consider as validation, analysis, explanation, verification, pruning, etc., of models [Rud19, Alb21, LAL