In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m- RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where there is an abundance of training samples, classes and feature spaces. The proposed methods are based on an expectation-maximization (EM) framework employing a multinomial probit likelihood and explicit pruning of non-relevant training samples. We demonstrate the methods on a low-dimensional artificial dataset. We then demonstrate the accuracy and sparsity of the method when applied to the challenging bioinformatics task of predicting protein subcellular localization.
|Translated title of the contribution||Inferring Sparse Kernel Combinations and Relevance Vectors: An application to subcellular localization of proteins|
|Title of host publication||International Conference on Machine Learning and Applications (ICMLA)|
|Number of pages||6|
|Publication status||Published - 2008|
Bibliographical noteName and Venue of Event: ICMLA, San Diego, California
Conference Proceedings/Title of Journal: ICMLA 2008