2 papers
cs.DB2026
MLSkip: Data Skipping for ML Filters via Lightweight Metadata
Mihail Stoian, Mark Gerarts, Pascal Ginter +3
Database vendors recently released AI functions that can be used in filter predicates. As such functions often rely on costly, black-box ML models, they unveil new data management…
cs.DB2025
SQL4NN: Validation and expressive querying of models as data
Mark Gerarts, Juno Steegmans, Jan Van den Bussche
We consider machine learning models, learned from data, to be an important, intensional, kind of data in themselves. As such, various analysis tasks on models can be thought of as…