ID: 1506.06179

Detectability thresholds and optimal algorithms for community structure in dynamic networks

June 20, 2015

View on ArXiv
Amir Ghasemian, Pan Zhang, Aaron Clauset, Cristopher Moore, Leto Peel
Statistics
Condensed Matter
Computer Science
Physics
Machine Learning
Disordered Systems and Neura...
Machine Learning
Social and Information Netwo...
Data Analysis, Statistics an...

We study the fundamental limits on learning latent community structure in dynamic networks. Specifically, we study dynamic stochastic block models where nodes change their community membership over time, but where edges are generated independently at each time step. In this setting (which is a special case of several existing models), we are able to derive the detectability threshold exactly, as a function of the rate of change and the strength of the communities. Below this threshold, we claim that no algorithm can identify the communities better than chance. We then give two algorithms that are optimal in the sense that they succeed all the way down to this limit. The first uses belief propagation (BP), which gives asymptotically optimal accuracy, and the second is a fast spectral clustering algorithm, based on linearizing the BP equations. We verify our analytic and algorithmic results via numerical simulation, and close with a brief discussion of extensions and open questions.

Similar papers 1