Community Recovery in Graphs with Locality
Information Theory
2016-06-02 v3 Machine Learning
Social and Information Networks
math.IT
Statistics Theory
Genomics
Statistics Theory
Abstract
Motivated by applications in domains such as social networks and computational biology, we study the problem of community recovery in graphs with locality. In this problem, pairwise noisy measurements of whether two nodes are in the same community or different communities come mainly or exclusively from nearby nodes rather than uniformly sampled between all nodes pairs, as in most existing models. We present an algorithm that runs nearly linearly in the number of measurements and which achieves the information theoretic limit for exact recovery.
Cite
@article{arxiv.1602.03828,
title = {Community Recovery in Graphs with Locality},
author = {Yuxin Chen and Govinda Kamath and Changho Suh and David Tse},
journal= {arXiv preprint arXiv:1602.03828},
year = {2016}
}
Comments
accepted in part to International Conference on Machine Learning (ICML), 2016