A Riemannian Optimization Approach for Role Model Extraction
Authors
Melissa Marchand, Wen Huang, Arnaud Browet, Paul Van Dooren, and Kyle A. Gallivan
Abstract
The ability to compute meaningful clusters of nodes is important in the analysis of large networks. A particular approach to this problem is the use of role models of a graph. For large networks, the algorithms must be specifically designed to extract role models while maintaining efficiency in storage and computations. Browet et al. have investigated the computation of role models for both moderately sized and large networks. They proposed an efficient iteration on low-rank matrices to compute an approximation to the required pairwise node similarity measure at MTNS 2014. In this paper, we summarize a new approach to compute an approximation to the pairwise node similarity measure for large networks based on Riemannian optimization. A comparison of our optimization approach with that of Browet et al. shows that our approach computes the same approximate solution in significantly less time.
Status
In Proceeding of The 22st International Symposium on Mathematical Theory of Networks and Systems (MTNS 2016).
Download
BibTex entry
- Technical Report
@TECHREPORT{MHBVG16,
author = "Melissa Marchand and Wen Huang and Arnaud Browet and Paul Van Dooren and Kyle A. Gallivan",
title = "A Riemannian Optimization Approach for Role Model Extraction",
institution = "U.C.Louvain",
number = "UCL-INMA-2016.01",
year = 2016,
}
@inproceedings{MHBVG16,
author = "Melissa Marchand and Wen Huang and Arnaud Browet and Paul Van Dooren and Kyle A. Gallivan",
title = "A Riemannian Optimization Approach for Role Model Extraction",
booktitle = "Proceedings of the 22nd International Symposium on Mathematical Theory of Networks and Systems",
pages = "58-64",
year = 2016,
}