Structural trends in network ensembles

Abstract

A collection of networks is considered a network ensemble if its members originate from a common natural or technical process such as repeated measurements, replication and mutation, or massive parallelism, possibly under varying conditions. We propose a spectral approach to identify structural trends, i. e. prevalent patterns of connectivity, in an ensemble by delineating classes of networks with similar role structure. Formal, experimental, and practical evidence of its potential is given. © 2009 Springer-Verlag Berlin Heidelberg.