发明名称 |
Latent factor dependency structure determination |
摘要 |
Disclosed is a general learning framework for computer implementation that induces sparsity on the undirected graphical model imposed on the vector of latent factors. A latent factor model SLFA is disclosed as a matrix factorization problem with a special regularization term that encourages collaborative reconstruction. Advantageously, the model may simultaneously learn the lower-dimensional representation for data and model the pairwise relationships between latent factors explicitly. An on-line learning algorithm is disclosed to make the model amenable to large-scale learning problems. Experimental results on two synthetic data and two real-world data sets demonstrate that pairwise relationships and latent factors learned by the model provide a more structured way of exploring high-dimensional data, and the learned representations achieve the state-of-the-art classification performance. |
申请公布号 |
US8977579(B2) |
申请公布日期 |
2015.03.10 |
申请号 |
US201213649823 |
申请日期 |
2012.10.11 |
申请人 |
NEC Laboratories America, Inc. |
发明人 |
He Yunlong;Qi Yanjun;Kavukcuoglu Koray |
分类号 |
G06F15/18;G06N99/00;A61M5/00;A61M25/10;A61M25/00 |
主分类号 |
G06F15/18 |
代理机构 |
|
代理人 |
Kolodka Joseph |
主权项 |
1. A computer implemented method of structured latent factor analysis comprising:
by a computer: learning one or more hidden dependency structures of latent factors of a set of data; modeling pairwise relationships among them and determining structural relationships through the use of a sparse Gaussian graphical model; outputting an indication of the latent factor relationships; wherein said pairwise relationship modeling is performed according to the following pairwise Markov Random Field (MRF) prior on a vector of factors sεK:p(sμ,Θ)=1Z(μ,Θ)exp(-∑i=1Kμisi-12∑i=1K∑j=1Kθijsisj)(4) with parameter μ=[μi], symmetric Θ=[θij], and partition function Z(μ,Θ) which normalizes the distribution, wherein p is a probability of a field configuration of (s|μ, Θ), K is a number of latent factors, s is an element of natural parameter K, and i and j are non-zero variables; and modeling the pairwise interaction simultaneously with the learning one or more hidden dependency structures of latent factors of a set of data. |
地址 |
Princeton NJ US |