Query Languages for Machine-Learning Models
By: Martin Grohe
In this paper, I discuss two logics for weighted finite structures: first-order logic with summation (FO(SUM)) and its recursive extension IFP(SUM). These logics originate from foundational work by Grädel, Gurevich, and Meer in the 1990s. In recent joint work with Standke, Steegmans, and Van den Bussche, we have investigated these logics as query languages for machine learning models, specifically neural networks, which are naturally represented as weighted graphs. I present illustrative examples of queries to neural networks that can be expressed in these logics and discuss fundamental results on their expressiveness and computational complexity.
Similar Papers
Recursive querying of neural networks via weighted structures
Logic in Computer Science
Lets computers explain how they learn.
Lecture Notes on Verifying Graph Neural Networks
Logic in Computer Science
Checks computer programs for mistakes using logic.
Two-Variable Logic for Hierarchically Partitioned and Ordered Data
Logic in Computer Science
Helps computers understand complex, layered information.