A4 Vertaisarvioitu artikkeli konferenssijulkaisussa
Efficient AUC Maximization with Regularized Least-Squares
Tekijät: Pahikkala T, Airola A, Suominen H, Boberg J, Salakoski T
Toimittaja: Anders Holst, Per Kreuger, Peter Funk
Konferenssin vakiintunut nimi: Scandinavian Conference on Artificial Intelligence
Julkaisuvuosi: 2008
Journal: Frontiers in Artificial Intelligence and Applications
Kokoomateoksen nimi: Frontiers in Artificial Intelligence and Applications
Tietokannassa oleva lehden nimi: TENTH SCANDINAVIAN CONFERENCE ON ARTIFICIAL INTELLIGENCE
Lehden akronyymi: FR ART INT
Vuosikerta: 173
Aloitussivu: 12
Lopetussivu: 19
Sivujen määrä: 8
ISBN: 978-1-58603-867-0
ISSN: 0922-6389
Area under the receiver operating characteristics curve (AUC) is a popular measure for evaluating the quality of binary classifiers, and intuitively, machine learning algorithms that maximize an approximation of AUC should have a good AUC performance when classifying new examples. However, designing Such algorithms in the framework of kernel methods has proven to be challenging. In this paper, we address AUC maximization with the regularized least-squares (RLS) algorithm also known as the least-squares Support vector machine. First. we introduce RLS-type binary classifier that maximizes all approximation of AUC and has a closed-form solution. Second, we show that this AUC-RLS algorithm is computationally as efficient as the standard RLS algorithm that maximizes an approximation of the accuracy. Third, we compare the performance of these two algorithms in the task of assigning topic labels for newswire articles in terms of AUC. Our algorithm outperforms the standard RLS in every classification experiment conducted. The performance gains are most substantial when the distribution of the class labels is unbalanced. In conclusion, modifying the RLS algorithm to maximize the approximation of AUC does not increase the computational complexity, and this alteration enhances the quality of the classifier.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
