Many data mining applications can benefit from adapting existing classifiers to new data with shifted distributions. In this paper, we present Adaptive Support Vector Machine (Adapt-SVM) as an efficient model for adapting a SVM classifier trained from one dataset to a new dataset where only limited labeled examples are available. By introducing a new regularizer into SVM's objective function, Adapt-SVM aims to minimize both the classification error over the training examples, and the discrepancy between the adapted and original classifier. We also propose a selective sampling strategy based on the loss minimization principle to seed the most informative examples for classifier adaptation. Experiments on an artificial classification task and on a benchmark video classification task shows that AdaptSVM outperforms several baseline methods in terms of accuracy and/or efficiency.
Jun Yang 0003, Rong Yan, Alexander G. Hauptmann