ISSN:2164-6457 (print)
ISSN:2164-6473 (online)
Journal of Applied Nonlinear Dynamics
Miguel A. F. Sanjuan (editor), Albert C.J. Luo (editor)
Miguel A. F. Sanjuan (editor)

Email: miguel.sanjuan@urjc.es

Albert C.J. Luo (editor)

Department of Mechanical and Industrial Engineering, Southern Illinois University Ed-wardsville, IL 62026-1805, USA

Fax: +1 618 650 2555 Email: aluo@siue.edu

Journal of Applied Nonlinear Dynamics 7(3) (2018) 269--285 | DOI:10.5890/JAND.2018.09.005

Filipe Alves Neto Verri$^{1}$,$^{2}$, Paulo Roberto Urio$^{3}$, Liang Zhao$^{4}$

$^{1}$ Institute of Mathematical and Computer Sciences, University of São Paulo, São Carlos, Brazil

$^{2}$ School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe AZ, USA

$^{3}$ Institute of Mathematical and Computer Sciences, University of São Paulo, São Carlos, Brazil

$^{4}$ Ribeir˜ao Preto School of Philosophy, Science and Literature, University of São Paulo, Ribeirão Preto, Brazil

Abstract

We study how effectively edge-centric dynamics solve semi-supervised learning tasks. The Edge Domination System is an algorithm to reveal patterns and obtain information of the underlying complex network. The algorithm consists of the simulation of a collective dynamical system based on particle competition for the dominance of edges. In this paper, we propose a vertex-centric version of this model and assess the differences between the edge-centric model. The edge-centric system offers better features in semi-supervised learning tasks, such as greater exploration behavior and faster convergence.

Acknowledgments

This research was supported by the S˜ao Paulo State Research Foundation (FAPESP), the Coordination for the Improvement of Higher Education Personnel (CAPES), and the Brazilian National Research Council (CNPq).

References

1.  [1] Gueleri, R.A., Cupertino, T.H., de Carvalho, A.C.P.L.F., and Zhao, L. (2014), A ocking-like technique to perform semi-supervised learning, International Joint Conference on Neural Networks (IJCNN), IEEE, 1579- 1586, DOI: 10.1109/IJCNN.2014.6889434.
2.  [2] Zhang, Z., Long, K.,Wang, J., and Dressler, F. (2014), On swarm intelligence inspired self-organized networking: Its bionic mechanisms, designing principles and optimization approaches, IEEE Commun. Surveys Tuts., 16(1), 513-537.
3.  [3] Breve, F., Quiles, M.G., and Zhao, L. (2015), Interactive image segmentation using particle competition and cooperation, International Joint Conference in Neural Networks, Proceedings, IEEE, 1-8.
4.  [4] Verri, F.A.N., Urio, P.R., and Zhao, L. (2016), Network Unfolding Map by Vertex-Edge Dynamics Modeling, IEEE Transactions on Neural Networks and Learning Systems, (99), 1-14, ISSN: 2162-237X, DOI: 10.1109/TNNLS.2016.2626341.
5.  [5] Silva, T.C. and Zhao, L. (2016), Machine Learning in Complex Networks, 1st ed., Springer, p. 331, ISBN: 978-3-319-17290-3, DOI: 10.1007/978-3-319-17290-3.
6.  [6] Urio, P.R., Verri, F.A.N., and Zhao, L. (2016), Features of edge-centric collective dynamics in machine learning tasks, International Conference on Nonlinear Science and Complexity, Proceedings.
7.  [7] Chapelle, O., Schölkopf, B., and Zien, A., eds. (2006), Semi-Supervised Learning, MIT Press: Cambridge, MA, p. 524, ISBN: 9780262033589, DOI: 10.7551/mitpress/9780262033589.001.0001.