SQL4NN: Validation and expressive querying of models as data
Not on the map. Why?
Abstract (arXiv)
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 queries over this intensional data, often combined with extensional data such as data for training or validation. We demonstrate that relational database systems and SQL can actually be well suited for many such tasks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 9 of its 29 references that are in the map. First posted on arXiv 20 Feb 2025.
Builds on
9 of 29 references.
References · 9
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
- 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
- 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
- 2021Introduction to Neural Network Verificationcited by 63
- 2021Foundations of Symbolic Languages for Model Interpretabilitycited by 26
- 2022Management of Machine Learning Lifecycle Artifacts: A Surveycited by 13
- 2023A Uniform Language to Explain Decision Treescited by 4
- 2019Declarative Data Analytics: a Surveycited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.