Matrix factorization with explicit user and item bias, learning is performed by stochastic gradient descent, optimized for the log likelihood. More...
Public Member Functions | |
override void | AddRating (int user_id, int item_id, double rating) |
Add a new rating and perform incremental training. | |
virtual bool | CanPredict (int user_id, int item_id) |
Check whether a useful prediction (i.e. not using a fallback/default answer) can be made for a given user-item combination. | |
Object | Clone () |
create a shallow copy of the object | |
override double | ComputeLoss () |
Compute the regularized loss. | |
override void | Iterate () |
Run one iteration (= pass over the training data). | |
override void | LoadModel (string filename) |
Get the model parameters from a file. | |
override double | Predict (int user_id, int item_id) |
Predict the rating of a given user for a given item. | |
override void | RemoveItem (int item_id) |
Remove an item from the recommender model, and delete all ratings of this item. | |
override void | RemoveRating (int user_id, int item_id) |
Remove an existing rating and perform "incremental" training. | |
override void | RemoveUser (int user_id) |
Remove a user from the recommender model, and delete all their ratings. | |
override void | RetrainItem (int item_id) |
Updates the latent factors of an item. | |
override void | RetrainUser (int user_id) |
Updates the latent factors on a user. | |
override void | SaveModel (string filename) |
Save the model parameters to a file. | |
override string | ToString () |
Return a string representation of the recommender. | |
override void | Train () |
Learn the model parameters of the recommender from the training data. | |
override void | UpdateRating (int user_id, int item_id, double rating) |
Update an existing rating and perform incremental training. | |
Protected Member Functions | |
override void | AddItem (int item_id) |
override void | AddUser (int user_id) |
override void | InitModel () |
Initialize the model data structure. | |
override void | Iterate (IList< int > rating_indices, bool update_user, bool update_item) |
Iterate once over rating data and adjust corresponding factors (stochastic gradient descent). | |
double | Predict (int user_id, int item_id, bool bound) |
Protected Attributes | |
double | global_bias |
The bias (global average). | |
double[] | item_bias |
the item biases | |
Matrix< double > | item_factors |
Matrix containing the latent item factors. | |
double | last_loss = double.NegativeInfinity |
Loss for the last iteration, used by bold driver heuristics. | |
double | max_rating |
Maximum rating value. | |
double | min_rating |
Minimum rating value. | |
IRatings | ratings |
rating data | |
double[] | user_bias |
the user biases | |
Matrix< double > | user_factors |
Matrix containing the latent user factors. | |
Properties | |
double | BiasReg [get, set] |
regularization constant for the bias terms | |
bool | BoldDriver [get, set] |
Use bold driver heuristics for learning rate adaption. | |
double | InitMean [get, set] |
Mean of the normal distribution used to initialize the factors. | |
double | InitStdDev [get, set] |
Standard deviation of the normal distribution used to initialize the factors. | |
double | LearnRate [get, set] |
Learn rate. | |
int | MaxItemID [get, set] |
Maximum item ID. | |
virtual double | MaxRating [get, set] |
Maximum rating value. | |
int | MaxUserID [get, set] |
Maximum user ID. | |
virtual double | MinRating [get, set] |
Minimum rating value. | |
uint | NumFactors [get, set] |
Number of latent factors. | |
uint | NumIter [get, set] |
Number of iterations over the training data. | |
bool | OptimizeMAE [get, set] |
If set to true, optimize model for MAE instead of RMSE. | |
virtual IRatings | Ratings [get, set] |
The rating data. | |
double | RegI [get, set] |
regularization constant for the item factors | |
double | RegU [get, set] |
regularization constant for the user factors | |
override double | Regularization [set] |
Regularization parameter. | |
bool | UpdateItems [get, set] |
true if items shall be updated when doing incremental updates | |
bool | UpdateUsers [get, set] |
true if users shall be updated when doing incremental updates |
Matrix factorization with explicit user and item bias, learning is performed by stochastic gradient descent, optimized for the log likelihood.
Implements a simple version Menon and Elkan's LFL model: Predicts binary labels, no advanced regularization, no side information.
Literature:
This recommender supports incremental updates.
override void AddRating | ( | int | user_id, | |
int | item_id, | |||
double | rating | |||
) | [inline, virtual, inherited] |
Add a new rating and perform incremental training.
user_id | the ID of the user who performed the rating | |
item_id | the ID of the rated item | |
rating | the rating value |
Reimplemented from IncrementalRatingPredictor.
virtual bool CanPredict | ( | int | user_id, | |
int | item_id | |||
) | [inline, virtual, inherited] |
Check whether a useful prediction (i.e. not using a fallback/default answer) can be made for a given user-item combination.
It is up to the recommender implementor to decide when a prediction is useful, and to document it accordingly.
user_id | the user ID | |
item_id | the item ID |
Implements IRecommender.
Reimplemented in BiPolarSlopeOne, Constant, GlobalAverage, ItemAverage, Random, SlopeOne, and UserAverage.
Object Clone | ( | ) | [inline, inherited] |
create a shallow copy of the object
override double ComputeLoss | ( | ) | [inline, virtual] |
Compute the regularized loss.
Reimplemented from BiasedMatrixFactorization.
override void InitModel | ( | ) | [inline, protected, virtual, inherited] |
Initialize the model data structure.
Reimplemented from MatrixFactorization.
Reimplemented in SocialMF.
override void Iterate | ( | ) | [inline, virtual, inherited] |
Run one iteration (= pass over the training data).
Reimplemented from MatrixFactorization.
Reimplemented in MultiCoreMatrixFactorization.
override void Iterate | ( | IList< int > | rating_indices, | |
bool | update_user, | |||
bool | update_item | |||
) | [inline, protected, virtual] |
Iterate once over rating data and adjust corresponding factors (stochastic gradient descent).
rating_indices | a list of indices pointing to the ratings to iterate over | |
update_user | true if user factors to be updated | |
update_item | true if item factors to be updated |
Reimplemented from BiasedMatrixFactorization.
override void LoadModel | ( | string | filename | ) | [inline, virtual, inherited] |
Get the model parameters from a file.
filename | the name of the file to read from |
Reimplemented from MatrixFactorization.
override double Predict | ( | int | user_id, | |
int | item_id | |||
) | [inline, virtual, inherited] |
Predict the rating of a given user for a given item.
If the user or the item are not known to the recommender, the global average is returned. To avoid this behavior for unknown entities, use CanPredict() to check before.
user_id | the user ID | |
item_id | the item ID |
Reimplemented from MatrixFactorization.
override void RemoveItem | ( | int | item_id | ) | [inline, virtual, inherited] |
Remove an item from the recommender model, and delete all ratings of this item.
It is up to the recommender implementor whether there should be model updates after this action, both options are valid.
item_id | the ID of the user to be removed |
Reimplemented from MatrixFactorization.
override void RemoveRating | ( | int | user_id, | |
int | item_id | |||
) | [inline, virtual, inherited] |
Remove an existing rating and perform "incremental" training.
user_id | the ID of the user who performed the rating | |
item_id | the ID of the rated item |
Reimplemented from IncrementalRatingPredictor.
override void RemoveUser | ( | int | user_id | ) | [inline, virtual, inherited] |
Remove a user from the recommender model, and delete all their ratings.
It is up to the recommender implementor whether there should be model updates after this action, both options are valid.
user_id | the ID of the user to be removed |
Reimplemented from MatrixFactorization.
override void RetrainItem | ( | int | item_id | ) | [inline, virtual, inherited] |
Updates the latent factors of an item.
item_id | the item ID |
Reimplemented from MatrixFactorization.
override void RetrainUser | ( | int | user_id | ) | [inline, virtual, inherited] |
Updates the latent factors on a user.
user_id | the user ID |
Reimplemented from MatrixFactorization.
override void SaveModel | ( | string | filename | ) | [inline, virtual, inherited] |
Save the model parameters to a file.
filename | the name of the file to write to |
Reimplemented from MatrixFactorization.
override string ToString | ( | ) | [inline] |
Return a string representation of the recommender.
The ToString() method of recommenders should list the class name and all hyperparameters, separated by space characters.
Reimplemented from BiasedMatrixFactorization.
override void UpdateRating | ( | int | user_id, | |
int | item_id, | |||
double | rating | |||
) | [inline, virtual, inherited] |
Update an existing rating and perform incremental training.
user_id | the ID of the user who performed the rating | |
item_id | the ID of the rated item | |
rating | the rating value |
Reimplemented from IncrementalRatingPredictor.
double global_bias [protected, inherited] |
The bias (global average).
double [] item_bias [protected, inherited] |
the item biases
Matrix<double> item_factors [protected, inherited] |
Matrix containing the latent item factors.
double last_loss = double.NegativeInfinity [protected, inherited] |
Loss for the last iteration, used by bold driver heuristics.
double max_rating [protected, inherited] |
Maximum rating value.
double min_rating [protected, inherited] |
Minimum rating value.
double [] user_bias [protected, inherited] |
the user biases
Matrix<double> user_factors [protected, inherited] |
Matrix containing the latent user factors.
double BiasReg [get, set, inherited] |
regularization constant for the bias terms
bool BoldDriver [get, set, inherited] |
Use bold driver heuristics for learning rate adaption.
Literature:
double InitMean [get, set, inherited] |
Mean of the normal distribution used to initialize the factors.
double InitStdDev [get, set, inherited] |
Standard deviation of the normal distribution used to initialize the factors.
double LearnRate [get, set, inherited] |
Learn rate.
int MaxItemID [get, set, inherited] |
Maximum item ID.
virtual double MaxRating [get, set, inherited] |
Maximum rating value.
Implements IRatingPredictor.
int MaxUserID [get, set, inherited] |
Maximum user ID.
virtual double MinRating [get, set, inherited] |
Minimum rating value.
Implements IRatingPredictor.
uint NumFactors [get, set, inherited] |
Number of latent factors.
uint NumIter [get, set, inherited] |
Number of iterations over the training data.
Implements IIterativeModel.
bool OptimizeMAE [get, set, inherited] |
If set to true, optimize model for MAE instead of RMSE.
The rating data.
Reimplemented in FactorWiseMatrixFactorization, ItemKNN, KNN, TimeAwareRatingPredictor, and UserKNN.
double RegI [get, set, inherited] |
regularization constant for the item factors
double RegU [get, set, inherited] |
regularization constant for the user factors
override double Regularization [set, inherited] |
Regularization parameter.
Reimplemented from MatrixFactorization.
bool UpdateItems [get, set, inherited] |
true if items shall be updated when doing incremental updates
Default should true. Set to false if you do not want any updates to the item model parameters when doing incremental updates.
Implements IIncrementalRatingPredictor.
bool UpdateUsers [get, set, inherited] |
true if users shall be updated when doing incremental updates
Default should be true. Set to false if you do not want any updates to the user model parameters when doing incremental updates.
Implements IIncrementalRatingPredictor.