`

Timezone: »

 
Oral
Graphons, mergeons, and so on!
Justin Eldridge · Mikhail Belkin · Yusu Wang

Tue Dec 06 01:40 AM -- 02:00 AM (PST) @ Area 3

In this work we develop a theory of hierarchical clustering for graphs. Our modelling 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.

Author Information

Justin Eldridge (The Ohio State University)
Mikhail Belkin (Ohio State University)
Yusu Wang (The Ohio State University)

More from the Same Authors