Title :
Semi-supervised Laplacian eigenmaps for dimensionality reduction
Author :
Zheng, Feng ; Chen, Na ; Li, Luoqing
Author_Institution :
Fac. of Math. & Comput. Sci., Hubei Univ., Wuhan
Abstract :
Dimensionality reduction with prior information is considered. The semi-supervised Laplacian eigenmap algorithm is proposed. It is shown that the performance of dimensionality reduction algorithms can be improved by taking into account the label information of the data. The data analysis and experiments show the validity of our algorithm.
Keywords :
Laplace equations; data analysis; data mining; data reduction; eigenvalues and eigenfunctions; graph theory; learning (artificial intelligence); matrix algebra; data analysis; dimensionality reduction algorithm; machine learning; semisupervised Laplacian eigenmap algorithm; weight matrix; weighted neighborhood graph; Laplace equations; Pattern analysis; Pattern recognition; Wavelet analysis; Label information; Laplacian eigenmaps; Manifold learning;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-2238-8
Electronic_ISBN :
978-1-4244-2239-5
DOI :
10.1109/ICWAPR.2008.4635894
