Skip to main content

Graph self-organizing maps for cyclic and unbounded graphs

Journal Article


Abstract


  • Self-Organizing Maps capable of processing graph structured information are a relatively new concept. This paper describes a novel concept on the processing of graph structured information using the self organizing map framework which allows the processing of much more general types of graphs, e.g. cyclic graphs, directed graphs. Previous approaches to this problem were limited to the processing of bounded graphs, their computational complexity can grow rapidly with the level of connectivity of the graphs concerned, and are restricted to the processing of positional graphs. The novel concept proposed in this paper, namely, by using the clusters formed in the state space of the self organizing map to represent the ``strengths'' of the activation of the neighboring vertices, rather than as in previous approaches, using the state space of the surrounding vertices to represent such ``strengths'' of activations. Such an approach resulted in reduced computational demand, and in allowing the processing of non-positional graphs.

Publication Date


  • 2009

Citation


  • Hagenbuchner, M., Sperduti, A. & Tsoi, A. (2009). Graph self-organizing maps for cyclic and unbounded graphs. Neurocomputing, 72 (7-9), 1419-1430.

Scopus Eid


  • 2-s2.0-61849163336

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/1816

Number Of Pages


  • 11

Start Page


  • 1419

End Page


  • 1430

Volume


  • 72

Issue


  • 7-9

Place Of Publication


  • http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V10-4VBMNF8-1&_user=202616&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000014118&_version=1&_urlVersion=0&_userid=202616&md5=32fae7f7c931b4a21c1d014864953a81

Abstract


  • Self-Organizing Maps capable of processing graph structured information are a relatively new concept. This paper describes a novel concept on the processing of graph structured information using the self organizing map framework which allows the processing of much more general types of graphs, e.g. cyclic graphs, directed graphs. Previous approaches to this problem were limited to the processing of bounded graphs, their computational complexity can grow rapidly with the level of connectivity of the graphs concerned, and are restricted to the processing of positional graphs. The novel concept proposed in this paper, namely, by using the clusters formed in the state space of the self organizing map to represent the ``strengths'' of the activation of the neighboring vertices, rather than as in previous approaches, using the state space of the surrounding vertices to represent such ``strengths'' of activations. Such an approach resulted in reduced computational demand, and in allowing the processing of non-positional graphs.

Publication Date


  • 2009

Citation


  • Hagenbuchner, M., Sperduti, A. & Tsoi, A. (2009). Graph self-organizing maps for cyclic and unbounded graphs. Neurocomputing, 72 (7-9), 1419-1430.

Scopus Eid


  • 2-s2.0-61849163336

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/1816

Number Of Pages


  • 11

Start Page


  • 1419

End Page


  • 1430

Volume


  • 72

Issue


  • 7-9

Place Of Publication


  • http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V10-4VBMNF8-1&_user=202616&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000014118&_version=1&_urlVersion=0&_userid=202616&md5=32fae7f7c931b4a21c1d014864953a81