Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars
arXiv: Social and Information Networks, Volume abs/1806.07955, 2018.
Recent work in graph models has found that probabilistic hyperedge replacement grammars (HRGs) can be extracted from graphs and used to generate new random graphs with graph properties and substructures close to the original. In this paper, we show how to add latent variables to the model, trained using Expectation-Maximization, to genera...More
Full Text (Upload PDF)
PPT (Upload PPT)