skip to content

Convex Relaxation for Community Detection with Covariates

Presented by: 
Purna Sarkar University of Texas at Austin
Friday 15th July 2016 - 16:00 to 16:30
INI Seminar Room 1
Community detection in networks is an important problem in many applied areas. We investigate this in the presence of node covariates. Recently, an emerging body of theoretical work has been focused on  leveraging information from both the edges in the network and the node covariates to infer community memberships. However, in most parameter regimes, one of the sources of information provides enough information to infer the hidden clusters, thereby making the other source redundant. We show that when the network and the covariates carry ``orthogonal'' pieces of information about the cluster memberships, one can get asymptotically consistent clustering by using them both, while each of them fails individually. 

This is joint work with Bowei Yan, University of Texas at Austin.
The video for this talk should appear here if JavaScript is enabled.
If it doesn't, something may have gone wrong with our embedded player.
We'll get it fixed as soon as possible.
University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons