Learning to classify structured data by graph propositionalization
2006 (English)In: Proc. IASTED Int. Conf. Comput. Intell., CI, 2006, 393-398 p.Conference paper (Refereed)
Existing methods for learning from structured data are limited with respect to handling large or isolated substructures and also impose constraints on search depth and induced structure length. An approach to learning from structured data using a graph based propositionalization method, called finger printing, is introduced that addresses the limitations of current methods. The method is implemented in a system called DIFFER, which is demonstrated to compare favorable to existing state-of-art methods on some benchmark data sets. It is shown that further improvements can be obtained by combining the features generated by finger printing with features generated by previous methods.
Place, publisher, year, edition, pages
2006. 393-398 p.
, Proceedings of the 2nd IASTED International Conference on Computational Intelligence, CI 2006
Classification, Graph, Machine learning, Structured data, Artificial intelligence, Education, Graph theory, Intelligent control, Learning systems, Printing, Art methods, Benchmark datums, Existing methods, Finger printings, Graph based, Induced structures, Propositionalization, Structured datums, Sub structures, Computational geometry
IdentifiersURN: urn:nbn:se:kth:diva-155345ISI: 000243777100069ScopusID: 2-s2.0-56349162143ISBN: 0889866023ISBN: 9780889866027OAI: oai:DiVA.org:kth-155345DiVA: diva2:763705
2nd IASTED International Conference on Computational Intelligence, CI 2006, 20-22 November 2006, San Francisco, CA, USA
QC 201411172014-11-172014-11-052014-11-17Bibliographically approved