Semi-supervised manifold learning based on 2-fold weights

In locally linear embedding framework, a semi-supervised manifold learning method based on 2-fold weights is proposed. The basic idea is not only to preserve intra-class local information in the processing of dimensionality reduction but also to predict the label of a data point according to its neighbours. Different from existing approaches, our method finds the k-nearest neighbours of each point in k-multiplicity minimum spanning trees (MST) instead of the complete Euclidean graph. Two-fold weights are learned. One is the reconstruction weights for finding the embedding. The other is the derivative weights for class label propagation. The experimental results on synthetic and real data, multi-class data sets demonstrate the effectiveness of the proposed approach.