TY - GEN
T1 - Graph-based multilevel dimensionality reduction with applications to eigenfaces and Latent Semantic Indexing
AU - Sakellaridi, Sophia
AU - Fang, Haw Ren
AU - Saad, Yousef
PY - 2008
Y1 - 2008
N2 - Dimension reduction techniques have been successfully applied to face recognition and text information retrieval. The process can he time-consuming when the data set is large. This paper presents a multilevel framework to reduce the size of the data set, prior to performing dimension reduction. The algorithm exploits nearest-neighbor graphs. It recursively coarsens the data by finding a maximal matching level by level. The coarsened data at the lowest level is then projected using a known linear dimensionality reduction method. The same linear mapping is performed on the original data set, and on any new test data. The methods are illustrated on two applications: Eigenfaces (face recognition) and Latent Semantic Indexing (text mining). Experimental results indicate that the multilevel techniques proposed here offer a very appealing cost to quality ratio.
AB - Dimension reduction techniques have been successfully applied to face recognition and text information retrieval. The process can he time-consuming when the data set is large. This paper presents a multilevel framework to reduce the size of the data set, prior to performing dimension reduction. The algorithm exploits nearest-neighbor graphs. It recursively coarsens the data by finding a maximal matching level by level. The coarsened data at the lowest level is then projected using a known linear dimensionality reduction method. The same linear mapping is performed on the original data set, and on any new test data. The methods are illustrated on two applications: Eigenfaces (face recognition) and Latent Semantic Indexing (text mining). Experimental results indicate that the multilevel techniques proposed here offer a very appealing cost to quality ratio.
UR - http://www.scopus.com/inward/record.url?scp=60649096266&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=60649096266&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2008.140
DO - 10.1109/ICMLA.2008.140
M3 - Conference contribution
AN - SCOPUS:60649096266
SN - 9780769534954
T3 - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
SP - 194
EP - 200
BT - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
T2 - 7th International Conference on Machine Learning and Applications, ICMLA 2008
Y2 - 11 December 2008 through 13 December 2008
ER -