MyMediaLite  3.08
Public Member Functions | Protected Member Functions | Protected Attributes | Properties
LeastSquareSLIM Class Reference

Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for the elastic net loss. More...

Inheritance diagram for LeastSquareSLIM:
SLIM IncrementalItemRecommender IIterativeModel ItemRecommender IIncrementalItemRecommender Recommender IIncrementalRecommender IRecommender

List of all members.

Public Member Functions

virtual void AddFeedback (ICollection< Tuple< int, int >> feedback)
 Add positive feedback events 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 float ComputeObjective ()
 Compute the regularized loss (regularized squared error on training data)
void Iterate (int item_id)
 Perform one iteration of coordinate descent for a given set of item parameters over the training data.
override void Iterate ()
 Iterate this instance.
 LeastSquareSLIM ()
 Default constructor.
override void LoadModel (string filename)
 Get the model parameters from a file.
float Predict (int user_id, int item_id, int exclude_item_id)
 Predict the specified user_id, item_id without taking exclude_item_id into consideration. This is needed for the coordinate descent update rule (equation 5 from Friedman et al. (2010)).
override float Predict (int user_id, int item_id)
 Predict rating or score for a given user-item combination.
IList< Tuple< int, float > > Recommend (int user_id, int n=-1, ICollection< int > ignore_items=null, ICollection< int > candidate_items=null)
 Recommend items for a given user.
virtual
System.Collections.Generic.IList
< Tuple< int, float > > 
Recommend (int user_id, int n=-1, System.Collections.Generic.ICollection< int > ignore_items=null, System.Collections.Generic.ICollection< int > candidate_items=null)
virtual void RemoveFeedback (ICollection< Tuple< int, int >> feedback)
 Remove all feedback events by the given user-item combinations.
override void RemoveItem (int item_id)
 Remove all feedback by one item.
override void RemoveUser (int user_id)
 Remove all feedback by one 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.
void Train (int item_id)
 Learns the set of parameters for a given item.

Protected Member Functions

override void AddItem (int item_id)
override void AddUser (int user_id)
override void InitModel ()
virtual void RetrainItem (int item_id)
 Retrain the latent factors of a given item.
virtual void UpdateParameters (int item_id, int other_item_id)
 Update item parameters according to the coordinate descent update rule.

Protected Attributes

Matrix< float > item_weights
 Item weight matrix (the W matrix in the original paper)
ItemKNN itemKNN
 The item KNN used in the feature selection step.
uint neighbors = 50
 How many neighbors to use in the kNN feature selection.
double reg_l1 = 0.01
 Regularization parameter for the L1 regularization term (lambda in the original paper)
double reg_l2 = 0.001
 Regularization parameter for the L2 regularization term (beta/2 in the original paper)

Properties

virtual IPosOnlyFeedback Feedback [get, set]
 the feedback data to be used for training
double InitMean [get, set]
 Mean of the normal distribution used to initialize the latent factors.
double InitStdDev [get, set]
 Standard deviation of the normal distribution used to initialize the latent factors.
uint K [get, set]
 How many neighbors to use in the kNN feature selection.
int MaxItemID [get, set]
 Maximum item ID.
int MaxUserID [get, set]
 Maximum user ID.
uint NumIter [get, set]
 Number of iterations over the training data.
double RegL1 [get, set]
 Regularization parameter for the L1 regularization term (lambda in the original paper)
double RegL2 [get, set]
 Regularization parameter for the L2 regularization term (beta/2 in the original paper)
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

Detailed Description

Sparse Linear Methods (SLIM) for item prediction (ranking) optimized for the elastic net loss.

The model is learned using a coordinate descent algorithm with soft thresholding (Friedman et al. 2010).

Literature:

This recommender supports incremental updates.


Constructor & Destructor Documentation

LeastSquareSLIM ( ) [inline]

Default constructor.


Member Function Documentation

virtual void AddFeedback ( ICollection< Tuple< int, int >>  feedback) [inline, virtual, inherited]

Add positive feedback events and perform incremental training.

Parameters:
feedbackcollection of user id - item id tuples

Implements IIncrementalItemRecommender.

Reimplemented in UserKNN, ItemKNN, MostPopular, and MF.

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.

Parameters:
user_idthe user ID
item_idthe item ID
Returns:
true if a useful prediction can be made, false otherwise

Implements IRecommender.

Reimplemented in ExternalItemRecommender, ExternalRatingPredictor, BiPolarSlopeOne, SlopeOne, Constant, GlobalAverage, UserAverage, ItemAverage, and Random.

Object Clone ( ) [inline, inherited]

create a shallow copy of the object

override float ComputeObjective ( ) [inline, virtual]

Compute the regularized loss (regularized squared error on training data)

Returns:
the objective

Implements SLIM.

void Iterate ( int  item_id) [inline]

Perform one iteration of coordinate descent for a given set of item parameters over the training data.

override void Iterate ( ) [inline, virtual]

Iterate this instance.

Implements SLIM.

override void LoadModel ( string  filename) [inline, virtual]

Get the model parameters from a file.

Parameters:
filenamethe name of the file to read from

Reimplemented from SLIM.

float Predict ( int  user_id,
int  item_id,
int  exclude_item_id 
) [inline]

Predict the specified user_id, item_id without taking exclude_item_id into consideration. This is needed for the coordinate descent update rule (equation 5 from Friedman et al. (2010)).

Parameters:
user_idUser_id.
item_idItem_id.
exclude_item_idCurrent item ID which shouldn't .
override float Predict ( int  user_id,
int  item_id 
) [inline, virtual]

Predict rating or score for a given user-item combination.

Parameters:
user_idthe user ID
item_idthe item ID
Returns:
the predicted score/rating for the given user-item combination

Reimplemented from SLIM.

IList<Tuple<int, float> > Recommend ( int  user_id,
int  n = -1,
ICollection< int >  ignore_items = null,
ICollection< int >  candidate_items = null 
) [inherited]

Recommend items for a given user.

Parameters:
user_idthe user ID
nthe number of items to recommend, -1 for as many as possible
ignore_itemscollection if items that should not be returned; if null, use empty collection
candidate_itemsthe candidate items to choose from; if null, use all items
Returns:
a sorted list of (item_id, score) tuples

Implemented in WeightedEnsemble, and Ensemble.

virtual void RemoveFeedback ( ICollection< Tuple< int, int >>  feedback) [inline, virtual, inherited]

Remove all feedback events by the given user-item combinations.

Parameters:
feedbackcollection of user id - item id tuples

Implements IIncrementalItemRecommender.

Reimplemented in UserKNN, MostPopular, ItemKNN, and MF.

override void RemoveItem ( int  item_id) [inline, virtual]

Remove all feedback by one item.

Parameters:
item_idthe item ID

Reimplemented from IncrementalItemRecommender.

override void RemoveUser ( int  user_id) [inline, virtual]

Remove all feedback by one user.

Parameters:
user_idthe user ID

Reimplemented from IncrementalItemRecommender.

virtual void RetrainItem ( int  item_id) [inline, protected, virtual]

Retrain the latent factors of a given item.

Parameters:
item_idthe item ID
override void SaveModel ( string  filename) [inline, virtual]

Save the model parameters to a file.

Parameters:
filenamethe name of the file to write to

Reimplemented from SLIM.

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 Recommender.

void Train ( int  item_id) [inline]

Learns the set of parameters for a given item.

virtual void UpdateParameters ( int  item_id,
int  other_item_id 
) [inline, protected, virtual]

Update item parameters according to the coordinate descent update rule.

Parameters:
item_idthe ID of the first item
other_item_idthe ID of the second item

Member Data Documentation

Matrix<float> item_weights [protected, inherited]

Item weight matrix (the W matrix in the original paper)

ItemKNN itemKNN [protected, inherited]

The item KNN used in the feature selection step.

uint neighbors = 50 [protected]

How many neighbors to use in the kNN feature selection.

double reg_l1 = 0.01 [protected]

Regularization parameter for the L1 regularization term (lambda in the original paper)

double reg_l2 = 0.001 [protected]

Regularization parameter for the L2 regularization term (beta/2 in the original paper)


Property Documentation

virtual IPosOnlyFeedback Feedback [get, set, inherited]

the feedback data to be used for training

double InitMean [get, set, inherited]

Mean of the normal distribution used to initialize the latent factors.

double InitStdDev [get, set, inherited]

Standard deviation of the normal distribution used to initialize the latent factors.

uint K [get, set]

How many neighbors to use in the kNN feature selection.

int MaxItemID [get, set, inherited]

Maximum item ID.

int MaxUserID [get, set, inherited]

Maximum user ID.

uint NumIter [get, set, inherited]

Number of iterations over the training data.

Implements IIterativeModel.

double RegL1 [get, set]

Regularization parameter for the L1 regularization term (lambda in the original paper)

double RegL2 [get, set]

Regularization parameter for the L2 regularization term (beta/2 in the original paper)

bool UpdateItems [get, set, inherited]

true if items shall be updated when doing incremental updates

Set to false if you do not want any updates to the item model parameters when doing incremental updates.

Implements IIncrementalRecommender.

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 IIncrementalRecommender.


The documentation for this class was generated from the following file: