AI RESEARCH

A Logical View of GNN-Style Computation and the Role of Activation Functions

arXiv CS.LG

ArXi:2512.19332v2 Announce Type: replace We study the numerical and Boolean expressiveness of MPLang, a declarative language that captures the computation of graph neural networks (GNNs) through linear message passing and activation functions. We begin with A-MPLang, the fragment without activation functions, and give a characterization of its expressive power in terms of walk-summed features.