TY - GEN
T1 - Heterogeneous component analysis
AU - Oba, Shigeyuki
AU - Kawanabe, Motoaki
AU - Müller, Klaus Robert
AU - Ishii, Shin
PY - 2009
Y1 - 2009
N2 - In bioinformatics it is often desirable to combine data from various measurement sources and thus structured feature vectors are to be analyzed that possess different intrinsic blocking characteristics (e.g., different patterns of missing values, observation noise levels, effective intrinsic dimensionalities). We propose a new machine learning tool, heterogeneous component analysis (HCA), for feature extraction in order to better understand the factors that underlie such complex structured heterogeneous data. HCA is a linear block-wise sparse Bayesian PCA based not only on a probabilistic model with block-wise residual variance terms but also on a Bayesian treatment of a block-wise sparse factor-loading matrix. We study various algorithms that implement our HCA concept extracting sparse heterogeneous structure by obtaining common components for the blocks and specific components within each block. Simulations on toy and bioinformatics data underline the usefulness of the proposed structured matrix factorization concept.
AB - In bioinformatics it is often desirable to combine data from various measurement sources and thus structured feature vectors are to be analyzed that possess different intrinsic blocking characteristics (e.g., different patterns of missing values, observation noise levels, effective intrinsic dimensionalities). We propose a new machine learning tool, heterogeneous component analysis (HCA), for feature extraction in order to better understand the factors that underlie such complex structured heterogeneous data. HCA is a linear block-wise sparse Bayesian PCA based not only on a probabilistic model with block-wise residual variance terms but also on a Bayesian treatment of a block-wise sparse factor-loading matrix. We study various algorithms that implement our HCA concept extracting sparse heterogeneous structure by obtaining common components for the blocks and specific components within each block. Simulations on toy and bioinformatics data underline the usefulness of the proposed structured matrix factorization concept.
UR - http://www.scopus.com/inward/record.url?scp=84889725544&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84889725544
SN - 160560352X
SN - 9781605603520
T3 - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
BT - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
T2 - 21st Annual Conference on Neural Information Processing Systems, NIPS 2007
Y2 - 3 December 2007 through 6 December 2007
ER -