Showing cs.LOShow all
3 papers · 1 filter
cs.LO2026
How Expressive Are Graph Neural Networks in the Presence of Node Identifiers?
Arie Soeteman, Michael Benedikt, Martin Grohe +1
Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation over neighbors. GNNs have close connections to…
cs.LO2025
From learnable objects to learnable random objects
Aaron Anderson, Michael Benedikt
We consider the relationship between learnability of a "base class" of functions on a set , and learnability of a class of statistical functions derived from the base class. For…
cs.LO2024
Synthesizing nested relational queries from implicit specifications: via model theory and via proof theory
Michael Benedikt, Cécilia Pradic, Christoph Wernhard
Derived datasets can be defined implicitly or explicitly. An implicit definition (of dataset O in terms of datasets I) is a logical specification involving two distinguished sets o…