Automatically Design Distance Functions for Graph-based Semi-Supervised Learning

Automatically Design Distance Functions for Graph-based Semi-Supervised Learning

Author Miquilini, Patricia Autor UNIFESP Google Scholar
Rossi, Rafael G. Google Scholar
Quiles, Marcos G. Autor UNIFESP Google Scholar
de Melo, Vinicius V. Autor UNIFESP Google Scholar
Basgalupp, Marcio P. Autor UNIFESP Google Scholar
Abstract Automatic data classification is often performed by supervised learning algorithms, producing a model to classify new instances. Reflecting that labeled instances are expensive, semi supervised learning (SSL) methods prove to be an alternative to performing data classification, once the learning demands only a few labeled instances. There are many SSL algorithms, and graph-based ones have significant features. In particular, graph-based models grant to identify classes of different distributions without prior knowledge of statistical model parameters. However, a drawback that might influence their classification performance relays on the construction of the graph, which requires the measurement of distances (or similarities) between instances. Since a particular distance function can enhance the performance for some data sets and decrease to others, here, we introduce a novel approach, called GEAD, a Grammatical Evolution for Automatically designing Distance functions for Graph-based semi-supervised learning. We perform extensive experiments with 100 public data sets to assess the performance of our approach, and we compare it with traditional distance functions in the literature. Results show that GEAD is capable of designing distance functions that significantly outperform the baseline manually-designed ones regarding different predictive measures, such as Micro-F-1, and Macro-F-1.
xmlui.dri2xhtml.METS-1.0.item-coverage New York
Language English
Sponsor Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq)
Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP)
Grant number FAPESP: 2016/02870-0
FAPESP: 2016/00868-9
Date 2017
Published in 2017 16th Ieee International Conference On Trust, Security And Privacy In Computing And Communications / 11th Ieee International Conference On Big Data Science And Engineering / 14th Ieee International Conference On Embedded Software And Systems. New York, v. , p. 933-940, 2017.
ISSN 2324-9013 (Sherpa/Romeo, impact factor)
Publisher Ieee
Extent 933-940
Origin http://dx.doi.org/10.1109/Trustcom/BigDataSE/ICESS.2017.333
Access rights Closed access
Type Conference paper
Web of Science ID WOS:000428367500121
URI https://repositorio.unifesp.br/handle/11600/55289

Show full item record




File

File Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Search


Browse

Statistics

My Account