Skip to main content

🏢 Tampere University

Logical characterizations of recurrent graph neural networks with reals and floats
·334 words·2 mins· loading · loading
AI Theory Representation Learning 🏢 Tampere University
Recurrent Graph Neural Networks (GNNs) with real and floating-point numbers are precisely characterized by rule-based and infinitary modal logics, respectively, enabling a deeper understanding of thei…