Abstract
In this paper we show an efficient method for inducing classifiers that directly optimize the area under the ROC curve. Recently, AUC gained importance in the classification community as a mean to compare the performance of classifiers. Because most classification methods do not optimize this measure directly, several classification learning methods are emerging that directly optimize the AUC. These methods, however, require many costly computations of the AUC, and hence, do not scale well to large datasets. In this paper, we develop a method to increase the efficiency of computing AUC based on a polynomial approximation of the AUC. As a proof of concept, the approximation is plugged into the construction of a scalable linear classifier that directly optimizes AUC using a gradient descent method. Experiments on real-life datasets show a high accuracy and efficiency of the polynomial approximation.
Chapter PDF
Similar content being viewed by others
Keywords
- Receiver Operating Characteristic Curve
- Linear Discriminant Analysis
- Polynomial Approximation
- Gradient Descent Method
- Multivariate Performance Measure
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Ataman, K., Street, W.N., Zhang, Y.: Learning to rank by maximizing auc with linear programming. In: IJCNN 2006. IEEE International Joint Conference on Neural Networks, pp. 123–129. IEEE Computer Society Press, Los Alamitos (2006)
Bradley, A.P.: Use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition 30(7), 1145–1159 (1997)
Brefeld, U., Scheffer, T.: AUC Maximizing Support Vector Learning. In: Proc. ICML workshop on ROC Analysis in Machine Learning (2005)
Cortes, C., Mohri, M.: Auc optimization vs. error rate minimization. In: Advances in Neural Information Processing Systems, vol. 16, MIT Press, Cambridge (2004)
Ferri, C., Flach, P., Hernandez-Orallo, J.: Learning decision trees using the area under the ROC curve. In: ICML, pp. 139–146 (2002)
Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1), 29–36 (1982)
Herschtal, A., Raskutti, B.: Optimising area under the roc curve using gradient descent. In: ICML, pp. 49–56. ACM Press, New York (2004)
Jaroszewicz, S.: Polynomial association rules with applications to logistic regression. In: KDD (2006)
Joachims, T.: A support vector method for multivariate performance measures. In: ICML (2005)
Rakotomamonjy, A.: Optimizing Area Under Roc Curve with SVMs. In: Workshop on ROC Analysis in Artificial Intelligence (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Calders, T., Jaroszewicz, S. (2007). Efficient AUC Optimization for Classification. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds) Knowledge Discovery in Databases: PKDD 2007. PKDD 2007. Lecture Notes in Computer Science(), vol 4702. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74976-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-74976-9_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74975-2
Online ISBN: 978-3-540-74976-9
eBook Packages: Computer ScienceComputer Science (R0)