Package es.upm.etsisi.cf4j.recommender.matrixFactorization

Class DeepMF

java.lang.Object

es.upm.etsisi.cf4j.recommender.Recommender

es.upm.etsisi.cf4j.recommender.matrixFactorization.DeepMF

public class DeepMF
extends Recommender

Implements Lara-Cabrera, R., González-Prieto, Á., & Ortega, F. (2020). Deep matrix factorization approach for collaborative filtering recommender systems. Applied Sciences, 10(14), 4926.

Field Summary

Fields inherited from class es.upm.etsisi.cf4j.recommender.Recommender

datamodel

Constructor Summary

Constructors

Constructor	Description
DeepMF(DataModel datamodel, int[] numFactors, int[] numIters, double[] learningRate, double[] regularization)	Model constructor
DeepMF(DataModel datamodel, int[] numFactors, int[] numIters, double[] learningRate, double[] regularization, long seed)	Model constructor
DeepMF(DataModel datamodel, Map<String,Object> params)	Model constructor from a Map containing the model's hyper-parameters values.

Method Summary

Modifier and Type	Method	Description
void	fit()	Estimates model parameters given the hyper-parameters
double	predict(int userIndex, int itemIndex)	Computes a rating prediction
String	toString()

Methods inherited from class es.upm.etsisi.cf4j.recommender.Recommender

getDataModel, predict

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

DeepMF

public DeepMF(DataModel datamodel,
              Map<String,Object> params)

Model constructor from a Map containing the model's hyper-parameters values. Map object must contains the following keys:

• numFactors: int array with the number of latent factors of each factorization.
• numIters:: int array with the number of iterations of each factorization.
• learingRate: double array with the learning rate hyper-parameter of each factorization.
• regularization: double array with the regularization hyper-parameter of each factorization.
• seed (optional): random seed for random numbers generation. If missing, random value is used.

Parameters:

datamodel - DataModel instance

params - Model's hyper-parameters values

DeepMF

public DeepMF(DataModel datamodel,
              int[] numFactors,
              int[] numIters,
              double[] learningRate,
              double[] regularization)

Model constructor

Parameters:

datamodel - DataModel instance

numFactors - int array with the number of latent factors of each factorization

numIters - int array with the number of iterations of each factorization

learningRate - double array with the learning rate hyper-parameter of each factorization

regularization - double array with the regularization hyper-parameter of each factorization

DeepMF

public DeepMF(DataModel datamodel,
              int[] numFactors,
              int[] numIters,
              double[] learningRate,
              double[] regularization,
              long seed)

Model constructor

Parameters:

datamodel - DataModel instance

numFactors - int array with the number of latent factors of each factorization

numIters - int array with the number of iterations of each factorization

learningRate - double array with the learning rate hyper-parameter of each factorization

regularization - double array with the regularization hyper-parameter of each factorization

seed - Seed for random numbers generation

Method Detail

fit

public void fit()

Description copied from class: Recommender

Estimates model parameters given the hyper-parameters

Specified by:

fit in class Recommender

predict

public double predict(int userIndex,
                      int itemIndex)

Description copied from class: Recommender

Computes a rating prediction

Specified by:

predict in class Recommender

Parameters:

userIndex - Index of the user in the array of Users of the DataModel instance

itemIndex - Index of the item in the array of Items of the DataModel instance

Returns:

Prediction

toString

public String toString()

Overrides:

toString in class Object