Some Research Problems in Metric Learning and Manifold Learning
Hong Chang, Dit‐Yan Yeung · 2004
In the past few years, metric learning, semi-supervised learning, and manifold learning meth-ods have aroused a great deal of interest in the machine learning community. Many machine learning and pattern recognition algorithms rely on a distance metric. Instead of choosing the metric manually, a promising approach is to learn the metric from data automatically. Besides some early work on metric learning for classification, more and more efforts have been devoted in recent years to learning a distance metric for the semi-supervised learning setting. Semi-supervised learning is a learning paradigm between the supervised and unsupervised learning extremes. Algorithms of this class usually solve the classification or clustering problems with the aid of additional background knowledge. While there has been a whole set of interesting ideas on how to learn from data with supervisory information, we focus our study on semi-supervised learning in the metric learning context. Manifold learning mainly aims to automatically discover the low-dimensional nonlinear man-ifold in a high-dimensional data space and then embed the data points into a low-dimensional embedding space. Besides manifold learning for data representation, some researchers have