Graphons, mergeons, and so on!
Machine Learning
2017-05-24 v4 Data Structures and Algorithms
Statistics Theory
Statistics Theory
Abstract
In this work we develop a theory of hierarchical clustering for graphs. Our modeling assumption is that graphs are sampled from a graphon, which is a powerful and general model for generating graphs and analyzing large networks. Graphons are a far richer class of graph models than stochastic blockmodels, the primary setting for recent progress in the statistical theory of graph clustering. We define what it means for an algorithm to produce the "correct" clustering, give sufficient conditions in which a method is statistically consistent, and provide an explicit algorithm satisfying these properties.
Cite
@article{arxiv.1607.01718,
title = {Graphons, mergeons, and so on!},
author = {Justin Eldridge and Mikhail Belkin and Yusu Wang},
journal= {arXiv preprint arXiv:1607.01718},
year = {2017}
}