Developed and evaluated a new approach that learns the building blocks of graphs that can be used to understand and generate new realistic graphs.
Adding latent variables to an HRG model, trained using Expectation-Maximization, generates graphs that generalize better to test data.
We introduce the infinity mirror test for the analysis of graph generator performance and robustness when working with empirical networks.
Salvador Aguinaga, Corey Pennycuff and Tim Weninger, NetSci Conference, Indianapolis, IN, June 21-23, 2017. (Poster)
What is the concept net or category hierarchy we navigate to connect different ideas together?
Building dependency graphs with Python.
Graph algorithms that contract graphs according to a specific feature. This is similar to dimensionality reduction. These type of algorithms lend themselves to parallelization.
Generating Networks by Learning Hyperedge Replacement Grammars