Ranking learning algorithms: Using IBL and meta-learning on accuracy and time results

• Tipo: Artigo em Revista Científica Internacional
• Data: 2003

Autores

Brazdil, PB (Autor) FEP; Soares, C (Autor) FEP; Da Costa, JP (Autor) FCUP

Revista

Título: Machine Learning

Vol. 50

Páginas: 251-277

ISSN: 0885-6125

Editora: Springer Nature

Indexação

ISI Web of Knowledge - 255 Citações

ISI Web of Science

Scopus - 325 Citações

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

Outras Informações

ID Authenticus: P-000-HMB

DOI: 10.1023/a:1021713901879

Abstract (EN): We present a meta-learning method to support selection of candidate learning algorithms. It uses a k-Nearest Neighbor algorithm to identify the datasets that are most similar to the one at hand. The distance between datasets is assessed using a relatively small set of data characteristics, which was selected to represent properties that affect algorithm performance. The performance of the candidate algorithms on those datasets is used to generate a recommendation to the user in the form of a ranking. The performance is assessed using a multicriteria evaluation measure that takes not only accuracy, but also time into account. As it is not common in Machine Learning to work with rankings, we had to identify and adapt existing statistical techniques to devise an appropriate evaluation methodology. Using that methodology, we show that the meta-learning method presented leads to significantly better rankings than the baseline ranking method. The evaluation methodology is general and can be adapted to other ranking problems. Although here we have concentrated on ranking classification algorithms, the meta-learning framework presented can provide assistance in the selection of combinations of methods or more complex problem solving strategies.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 27