Semi-supervised learning with local and global consistency
Authors:
- 25 September 2013
- journal article
- section a
- Published by Taylor & Francis in International Journal of Computer Mathematics
- Vol. 91 (11) , 2389-2402
Abstract
In a lot of practical machine learning applications, such as web page classification, protein shape classification, unlabelled instances are easy to obtain, but labelled instances are rather too expensive to get. Thus, recently, semi-supervised learning (SSL) methods including graph-based algorithms have attracted many interests from researchers. However, most of these algorithms used the Gaussian function to calculate weights of the edge of the graph. In this paper, we proposed a novel weight for graph-based semi-supervised algorithms. In this new algorithm, the label information is added from problem into SSL algorithm, and the geodesic distance is utilized instead of Euclidean distance to calculate the distance between two instances. Furthermore, class prior knowledge is also added from problem into the target function. In this paper, we focus on learning with local and global consistency. We found that the effect of class prior knowledge maybe different between under low-label rate and high-label rate. Experiments on two University of California Irvine (UCI) data sets and United States Postal Service handwritten digit recognition show that our proposed algorithm is really effective.Keywords
This publication has 17 references indexed in Scilit:
- Manifold Regularized Multitask Learning for Semi-Supervised Multilabel Image ClassificationIEEE Transactions on Image Processing, 2012
- Transductive SVM for reducing the training effort in BCIJournal of Neural Engineering, 2007
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005
- Dimensionality Reduction for Semi-supervised Face RecognitionLecture Notes in Computer Science, 2005
- Semi-Supervised Learning on Riemannian ManifoldsMachine Learning, 2004
- Laplacian Eigenmaps for Dimensionality Reduction and Data RepresentationNeural Computation, 2003
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000
- Parallel implementation of backpropagation neural networks on a heterogeneous array of transputersIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1997
- The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenonIEEE Transactions on Geoscience and Remote Sensing, 1994