Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks
M. Lapenna, Francesco Faglioni, Ferdinando Zanchetta, R. Fioresi · arXiv (Cornell University) · 2023
We examine a Geometric Deep Learning model as a thermodynamic system treating the weights as non-quantum and non-relativistic particles. We employ the notion of temperature previously defined in [7] and study it in the various layers for GCN and GAT models. Potential future applications of our findings are discussed.