Improving kNN multi-label classification in Prototype Selection scenarios using class proposals. Issue 5 (May 2015)

• Record Type: Journal Article
• Authors: Calvo-Zaragoza, Jorge; Valero-Mas, Jose J.; Rico-Juan, Juan R.
• Is Part Of: Pattern recognition. Volume 48:Issue 5(2015:May)
• Page Start: 1608
• Page End: 1622
• Publication Date: 2015-05
• Subjects: K-Nearest Neighbor -- Multi-label classification -- Prototype Selection -- Class proposals; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2014.11.015
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Prototype Selection (PS) algorithms allow a faster Nearest Neighbor classification by keeping only the most profitable prototypes of the training set. In turn, these schemes typically lower the performance accuracy. In this work a new strategy for multi-label classifications tasks is proposed to solve this accuracy drop without the need of using all the training set. For that, given a new instance, the PS algorithm is used as a fast recommender system which retrieves the most likely classes. Then, the actual classification is performed only considering the prototypes from the initial training set belonging to the suggested classes. Results show that this strategy provides a large set of trade-off solutions which fills the gap between PS-based classification efficiency and conventional kNN accuracy. Furthermore, this scheme is not only able to, at best, reach the performance of conventional kNN with barely a third of distances computed, but it does also outperform the latter in noisy scenarios, proving to be a much more robust approach. Abstract : Graphical abstract: Abstract : Highlights: Improving Prototype Selection-based classification proposing likely labels of the reduced set. kNN search within the original training set restricted to those proposed labels. Scheme that provides a broad range of solution in the trade-off accuracy efficiency. Cost reduction in multi-label classification scenarios and robustness against noise. Our approach gets to reach accuracy of kNN with barely a third of distances computed.