Supervised Median Clustering

Prototype based clustering and classification algorithms constitute very intuitive and powerful machine learning tools for a variety of application areas. They combine simple training algorithms and easy interpretability by means of prototype inspection. However, the classical methods are restricted to data embedded in a real vector space and thus, have only limited applicability to complex data as occurs in bioinformatics or symbolic areas. Recently, extensions of unsupervised prototype based clustering to proximity data, i.e. data characterized in terms of a distance matrix only, have been proposed. Since the distance matrix constitutes a universal interface, this opens the way towards an application of efficient prototype based methods for general data. In this contribution, we transfer this idea to supervised scenarios, proposing a prototype based classification method for general proximity data.