Kernel-Based Metric Adaptation with Pairwise Constraints

Many supervised and unsupervised learning algorithms depend on the choice of an appropriate distance metric. While metric learning for supervised learning tasks has a long history, extending it to learning tasks with weaker supervisory information has only been studied very recently. In particular, several methods have been proposed for semi-supervised metric learning based on pairwise (dis)similarity information. In this paper, we propose a kernel-based approach for nonlinear metric learning, which performs locally linear translation in the kernel-induced feature space. We formulate the metric learning problem as a kernel learning problem and solve it efficiently by kernel matrix adaptation. Experimental results based on synthetic and real-world data sets show that our approach is promising for semi-supervised metric learning.