Recently, increasing attention has been focused on the problem of online aucmaximization, and a great deal of efficient algorithms has been proposed. In spite of the promising performance of those online algorithms, ...
详细信息
Recently, increasing attention has been focused on the problem of online aucmaximization, and a great deal of efficient algorithms has been proposed. In spite of the promising performance of those online algorithms, however, most of them are sensitive to the outliers, which make them unsuitable for the applications with noisy data. To tackle the issue, in this paper, an adaptive robust method for online aucmaximization, termed AROAM is suggested. Specifically, a ramp loss based objective function oriented to auc metric is firstly defined in AROAM, which has the strong ability of suppressing the influence of outliers. Then, concave-convex procedure is adopted for the convex approximation of the objective function. Finally, to further improve the performance of AROAM, an adaptive learning rate strategy is developed in each iteration, which can update the classifier effectively. Empirical studies on the benchmark data sets demonstrate the superiority of the proposed method in comparison with the state-of-the-arts.
暂无评论