matrix factorization and its applications by zachary 16 th nov, 2010
DESCRIPTION
What can matrix represent? System of equations User rating matrix Image Matrix structure in graph theory ◦ Adjacent matrix ◦ Distance matrixTRANSCRIPT
Matrix Factorization and Matrix Factorization and its applicationsits applicationsBy Zachary16th Nov, 2010
OutlineOutlineExpression power of matrixVarious matrix factorization
methodsApplication of matrix
factorization
What can matrix What can matrix represent?represent?System of equationsUser rating matrixImageMatrix structure in graph theory
◦Adjacent matrix◦Distance matrix
Different matrix factorization Different matrix factorization methodsmethodsLU decompositionSingular Value
Decomposition(SVD)Probabilistic Matrix
Factorization(PMF)Non-negative Matrix
Factorization(NMF)
Application of matrix Application of matrix factorizationfactorizationLU decomposition
◦Solving system of equationsSVD decomposition
◦Low rank matrix approximation◦Pseudo-inverse
Application of matrix Application of matrix factorizationfactorizationPMF
◦Recommendation systemNMF
◦Learning the parts of objects
PMFPMFConsider a typical
recommendation problem◦Given a n by m matrix R with some
entries unknown n rows represent n users m columns represent m movies Entry represent the ith user’s rating on
the jth movie◦We are interested in the unknown
entries’ possible values i.e. Predict users’ ratings
ijR
PMFPMFWe can model the problem as R=U’V
◦U (k by n) is the latent feature matrix for users How much the user likes action movie? How much the user likes comedy movie?
◦V (k by m) is the latent feature matrix for movies To what extent is the movie an action movie? To what extent is the movie a comedy movie?
PMFPMFIf we can learn U and V from
existing ratings, then we can compute unknown entries by multiplying these two matrices.
Let’s consider a probabilistic approach.
PMFPMF
PMFPMFWe want to maximize
Equivalent to minimizing
Can be solved using steepest descent method
Extension to PMFExtension to PMFWe can augment the model as
long as we have additional data matrix that share comment latent feature matrix
NMFNMFConsider the following problem
◦M = 2429 facial images◦Each image of size n = 19 by 19 = 361◦Matrix V = n by m is the original dataset◦We want to approximate V by two lower
rank matrix W (n by 49) and H (49 by m) V ~ WH Constraints
All entries of W and H are non-negative
NMFNMFHow well can W and H
approximate VHow can we interpret the result
NMFNMFAssumption
◦ ◦ ◦Maximize logarithm likelihood and
we get the objective function
Criticize of NMFCriticize of NMFNMF doesn’t always
give parts based resultSparseness constraints
For more information, refer to “Non-negative matrix factorization with sparseness constrains”
Questions?Questions?Thank you