3 papers
cs.LO2026
Recursive querying of neural networks via weighted structures
Martin Grohe, Christoph Standke, Juno Steegmans +1
Expressive querying of machine learning models - viewed as a form of intentional data - enables their verification and interpretation using declarative languages, thereby making le…
cs.LG2025
Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message-Passing Limit
Eran Rosenbluth, Martin Grohe
We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggreg…
cs.DB2024
The Importance of Parameters in Database Queries
Amir Gilad, Martin Grohe, Benny Kimelfeld +2
We propose and study a framework for quantifying the importance of the choices of parameter values to the result of a query over a database. These parameters occur as constants in…