2026-07-23T01:42:00Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:22950 2025-10-02T12:19:27Z ddc:004 open_access

Query Languages for Neural Networks Grohe, Martin Standke, Christoph Steegmans, Juno Van den Bussche, Jan Expressive power of query languages Machine learning models languages for interpretability explainable AI We lay the foundations for a database-inspired approach to interpreting and understanding neural network models by querying them using declarative languages. Towards this end we study different query languages, based on first-order logic, that mainly differ in their access to the neural network model. First-order logic over the reals naturally yields a language which views the network as a black box; only the input-output function defined by the network can be queried. This is essentially the approach of constraint query languages. On the other hand, a white-box language can be obtained by viewing the network as a weighted graph, and extending first-order logic with summation over weight terms. The latter approach is essentially an abstraction of SQL . In general, the two approaches are incomparable in expressive power, as we will show. Under natural circumstances, however, the white-box approach can subsume the black-box approach; this is our main result. We prove the result concretely for linear constraint queries over real functions definable by feedforward neural networks with a fixed number of hidden layers and piecewise linear activation functions. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Martin Grohe and Christoph Standke and Juno Steegmans and Jan Van den Bussche 2025 Is Part Of LIPIcs, Volume 328, 28th International Conference on Database Theory (ICDT 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ICDT.2025.9 urn:nbn:de:0030-drops-229508 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICDT.2025.9 eng https://creativecommons.org/licenses/by/4.0/legalcode