Non-negative sparse autoencoder neural networks for the detection of overlapping, hierarchical communities in networked datasets

Sarah Michele Rajtmajer, Brian Smith, Shashi Phoha

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

We propose the first use of a non-negative sparse autoencoder (NNSAE) neural network for community structure detection in complex networks. The NNSAE learns a compressed representation of a set of fixed-length, weighted random walks over the network, and communities are detected as subsets of network nodes corresponding to non-negligible elements of the basis vectors of this compression. The NNSAE model is efficient and online. When utilized for community structure detection, it is able to uncover potentially overlapping and hierarchical community structure in large networks.

Original languageEnglish (US)
Article number043141
JournalChaos
Volume22
Issue number4
DOIs
StatePublished - Oct 4 2012

All Science Journal Classification (ASJC) codes

  • Statistical and Nonlinear Physics
  • Mathematical Physics
  • General Physics and Astronomy
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Non-negative sparse autoencoder neural networks for the detection of overlapping, hierarchical communities in networked datasets'. Together they form a unique fingerprint.

Cite this