Decidability of graph neural networks via logical characterizations

We present results concerning the expressiveness and decidability of a popular graph learning formalism, graph neural networks (GNNs), exploiting connections with logic. We use a family of recently-discovered decidable logics involving ``Presburger quantifiers''. We show how to use the...

पूर्ण विवरण

ग्रंथसूची विवरण
मुख्य लेखकों: Benedikt, M, Lu, C-H, Motik, B, Tan, T
स्वरूप: Conference item
भाषा:English
प्रकाशित: Lipics 2024