Graph limit theory provides a rigorous framework for analysing sequences of large graphs by representing them as continuous objects known as graphons – symmetric measurable functions on the unit ...

Abstract: We propose a notion of universality for graph neural networks (GNNs) in the large random graphs limit, tailored for node-level tasks. When graphs are drawn from a latent space model, or from ...

This is a preview. Log in through your library . Abstract Many data are suitably modeled by functions consisting of straight-line segments. These functions may be called piecewise-linear. Smooth ...