Query Languages for Machine-Learning Models

Martin Grohe
1/14/2026
cs.LOcs.AIcs.DB

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Recursive querying of neural networks via weighted structures

90% match2026

Extracting Formulae in Many-Valued Logic from Deep Neural Networks

78% match2024

Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

78% match2024

The Gradient of Algebraic Model Counting

77% match1 repo32025

On the Correspondence Between Monotonic Max-Sum GNNs and Datalog

77% match2023

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

77% match1 repo92023

Cite this paper

@article{grohe2026query,
  title  = {Query Languages for Machine-Learning Models},
  author = {Martin Grohe},
  year   = {2026},
  eprint = {2601.09381},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.09381v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.09381.svg)](https://codeofpaper.com/paper/2601.09381)

Discussion