Multi-Label Classification by ART-based Neural Networks and Hierarchy Extraction

Benites, Fernando; Brucker, Florian; Sapozhnikova, Elena

Multi-Label Classification by ART-based Neural Networks and Hierarchy Extraction

Files

There are no files associated with this item.

Date

2010

Authors

Benites, Fernando

Brucker, Florian

Sapozhnikova, Elena

Publication type

Contribution to a conference collection

Published in

The 2010 International Joint Conference on Neural Networks : (IJCNN 2010) ; Barcelona, Spain, 18 - 23 July 2010 ; [associated with the 2010 IEEE World Congress on Computational Intelligence (IEEE WCCI 2010)] / IEEE (ed.). - Piscataway, NJ : IEEE, 2010. - pp. 2788-2796. - ISBN 978-1-4244-6916-1

Abstract

This paper presents a data mining system for multi-label classification and hierarchy extraction from the predictions provided by a multi-label classifier. Classes in multilabel classification tasks are often hierarchically organized and the hierarchy is assumed to be known. A much less investigated approach and a more challenging task, however, is to suppose that the underlying class taxonomy is unknown and that a data mining system can infer it automatically. In our setting, the proposed system is trained with multi-label data and is subsequently able to produce multi-label predictions along with hierarchical relationships between classes. The hierarchy extraction algorithm is based on building association rules from label co-occurrences. Within the framework we examine the performance of two recently introduced multi-label extensions of Adaptive Resonance Theory (ART)-based neural networks: Multi-Label Fuzzy ARTMAP (ML-FAM) and Multi-Label Fuzzy Adaptive Resonance Associative Map (ML-ARAM) in comparison with two state-of-the-art classifiers Multi-Label k-Nearest Neighbors (ML-kNN) and BoosTexter, taking into account the quality of hierarchy extraction. We also develop a novel distance measure for the quantitative evaluation of the derived class hierarchies and compare it with two other distance measures. To demonstrate the effectiveness of the proposed approach, experiments on several benchmark datasets have been performed.

Subject (DDC)

004 Computer Science

Keywords

Multi-label,Adaptive Resonance Theory,Document Classification

Cite This

ISO 690

BENITES, Fernando, Florian BRUCKER, Elena SAPOZHNIKOVA, 2010. Multi-Label Classification by ART-based Neural Networks and Hierarchy Extraction. In: IEEE, , ed.. The 2010 International Joint Conference on Neural Networks : (IJCNN 2010) ; Barcelona, Spain, 18 - 23 July 2010 ; [associated with the 2010 IEEE World Congress on Computational Intelligence (IEEE WCCI 2010)]. Piscataway, NJ:IEEE, pp. 2788-2796. ISBN 978-1-4244-6916-1

BibTex

@inproceedings{Benites2010Multi-3321,
  year={2010},
  title={Multi-Label Classification by ART-based Neural Networks and Hierarchy Extraction},
  isbn={978-1-4244-6916-1},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={The 2010 International Joint Conference on Neural Networks : (IJCNN 2010) ; Barcelona, Spain, 18 - 23 July 2010 ; [associated with the 2010 IEEE World Congress on Computational Intelligence (IEEE WCCI 2010)]},
  pages={2788--2796},
  editor={IEEE},
  author={Benites, Fernando and Brucker, Florian and Sapozhnikova, Elena}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/3321">
    <dcterms:title>Multi-Label Classification by ART-based Neural Networks and Hierarchy Extraction</dcterms:title>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Benites, Fernando</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-23T13:15:40Z</dcterms:available>
    <dc:contributor>Sapozhnikova, Elena</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Sapozhnikova, Elena</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-23T13:15:40Z</dc:date>
    <dc:creator>Benites, Fernando</dc:creator>
    <dcterms:issued>2010</dcterms:issued>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Brucker, Florian</dc:creator>
    <dcterms:abstract xml:lang="eng">This paper presents a data mining system for multi-label classification and hierarchy extraction from the predictions provided by a multi-label classifier. Classes in multilabel classification tasks are often hierarchically organized and the hierarchy is assumed to be known. A much less investigated approach and a more challenging task, however, is to suppose that the underlying class taxonomy is unknown and that a data mining system can infer it automatically. In our setting, the proposed system is trained with multi-label data and is subsequently able to produce multi-label predictions along with hierarchical relationships between classes. The hierarchy extraction algorithm is based on building association rules from label co-occurrences. Within the framework we examine the performance of two recently introduced multi-label extensions of Adaptive Resonance Theory (ART)-based neural networks: Multi-Label Fuzzy ARTMAP (ML-FAM) and Multi-Label Fuzzy Adaptive Resonance Associative Map (ML-ARAM) in comparison with two state-of-the-art classifiers Multi-Label k-Nearest Neighbors (ML-kNN) and BoosTexter, taking into account the quality of hierarchy extraction. We also develop a novel distance measure for the quantitative evaluation of the derived class hierarchies and compare it with two other distance measures. To demonstrate the effectiveness of the proposed approach, experiments on several benchmark datasets have been performed.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/3321"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:bibliographicCitation>Publ. in: Proceedings of the International Joint Conference on Neural Network, July 18-23, Barcelona, 2010, pp. 2788 2796</dcterms:bibliographicCitation>
    <dc:contributor>Brucker, Florian</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes