Title :
Multi-label Classification Using Ensembles of Pruned Sets
Author :
Read, Jesse ; Pfahringer, Bernhard ; Holmes, Geoff
Author_Institution :
Dept. of Comput. Sci., Univ. of Waikato, Hamilton
Abstract :
This paper presents a pruned sets method (PS) for multi-label classification. It is centred on the concept of treating sets of labels as single labels. This allows the classification process to inherently take into account correlations between labels. By pruning these sets, PS focuses only on the most important correlations, which reduces complexity and improves accuracy. By combining pruned sets in an ensemble scheme (EPS), new label sets can be formed to adapt to irregular or complex data. The results from experimental evaluation on a variety of multi-label datasets show that [E]PS can achieve better performance and train much faster than other multi-label methods.
Keywords :
data mining; pattern classification; ensemble scheme; multilabel classification; pruned sets method; Bioinformatics; Computer science; Data mining; Genomics; Layout; Nearest neighbor searches; Support vector machine classification; Support vector machines; Text categorization; Tin; multi-label classification; problem transformation;
Conference_Titel :
Data Mining, 2008. ICDM '08. Eighth IEEE International Conference on
Conference_Location :
Pisa
Print_ISBN :
978-0-7695-3502-9
DOI :
10.1109/ICDM.2008.74