On Consistency of Community Detection in Networks

Community detection is a fundamental problem in network analysis. The stochastic block model is a common tool for model-based community detection. However, the block model is limited by its assumption that all nodes within a community are stochastically equivalent, and provides a poor fit to networks with hubs or highly varying node degrees within communities, which are common in practice. The degree-corrected block model was proposed to address this shortcoming, and allows variation in node degrees within a community while preserving the overall block model community structure. In this talk, we establish general theory for checking consistency of community detection under the degree-corrected block model, and compare several community detection criteria under both the standard and the degree-corrected block models.

Speaker Bio: Dr. Zhao received his Ph.D. from University of Michigan on 2012. And currently he is an assistant professor at the Department of Statistics, George Mason University. His research interests include complex network analysis, high dimensional data analysis, and machine learning.

Presentation Slides: PDF

Note: Visitors from outside NIST must contact Cathy Graham; (301) 975-3800; at least 24 hours in advance.