Hyperparameter and Kernel Learning for Graph Based Semi-Supervised Classification英文文献资料.pdf

Hyperparameter and Kernel Learning for Graph Based Semi-Supervised Classification Ashish Kapoor , Yuan (Alan) Qi , Hyungil Ahn and Rosalind W. Picard MIT Media Laboratory, Cambridge, MA 02139 kapoor, hiahn, picard@ MIT CSAIL, Cambridge, MA 02139 alanqi@ Abstract There have been many graph-based approaches for semi-supervised clas- sification. One problem is that of hyperparameter learning: performance depends greatly on the hyperparameters of the similarity graph, trans- formation of the graph Laplacian and the noise model. We present a Bayesian framework for learning hyperparameters for graph-based semi- supervised classification. Given some labeled data, which can contain inaccurate labels, we pose the semi-supervised classification as an in- ference problem over the unknown labels. Expectation Propagation is used for approximate inference and the mean of the posterior is used for classification. The hyperparameters are learned using EM for evidence maximization. We also show that the posterior mean can be written in terms of the kernel matrix, providing a Bayesian classifier to classify new points. Tests on synthetic and real datasets show cases where there are significant improvements in performance over the existing approaches. 1 Introduction A lot of recent work on semi-supervised learning is based on regularization on graphs [5]. The basic idea is to first create a graph with the labeled and unlabeled data points as the vertices and with the edge weights encoding the similarity between the data points. Th