Answers are grounded in this paper and cite their sources.
This analysis evaluates the functions computed by graph neural networks, indicating their computational capabilities.
The main subject of this work are certain parameterized algorithms, known as Graph Neural Networks, which operate on graphs. Specifically, we analyze what functions on graphs these algorithms can compute, or in other words, we analyze their expressivity.
No takes yet. Share an insight, caveat, or question.
Eran Rosenbluth (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: