merlin.models.tf.MatrixFactorizationModel

merlin.models.tf.MatrixFactorizationModel(schema: merlin.schema.schema.Schema, dim: int, query_id_tag=<Tags.USER_ID: 'user_id'>, item_id_tag=<Tags.ITEM_ID: 'item_id'>, embeddings_initializers: Optional[Union[Dict[str, Callable[[Any], None]], Callable[[Any], None]]] = None, embeddings_l2_reg: float = 0.0, post: Optional[Union[merlin.models.tf.blocks.core.base.Block, str, Sequence[str]]] = None, prediction_tasks: Optional[Union[merlin.models.tf.prediction_tasks.base.PredictionTask, List[merlin.models.tf.prediction_tasks.base.PredictionTask], merlin.models.tf.prediction_tasks.base.ParallelPredictionBlock]] = None, logits_temperature: float = 1.0, samplers: Sequence[merlin.models.tf.blocks.sampling.base.ItemSampler] = (), **kwargs) → merlin.models.tf.models.base.RetrievalModel[source]

Builds a matrix factorization model.

Example Usage::

mf = MatrixFactorizationModel(schema, dim=128) mf.compile(optimizer=”adam”) mf.fit(train_data, epochs=10)

Parameters

  • schema (Schema) – The Schema with the input features

  • dim (int) – The dimension of the embeddings.

  • query_id_tag (Tag) – The tag to select query features, by default Tags.USER

  • item_id_tag (Tag) – The tag to select item features, by default Tags.ITEM

  • embeddings_initializers (Optional[Dict[str, Callable[[Any], None]]] = None) – An initializer function or a dict where keys are feature names and values are callable to initialize embedding tables

  • embeddings_l2_reg (float = 0.0) – Factor for L2 regularization of the embeddings vectors (from the current batch only)

  • post (Optional[Block], optional) – The optional Block to apply on both outputs of Two-tower model

  • prediction_tasks (optional) – The optional PredictionTask or list of PredictionTask to apply on the model.

  • logits_temperature (float) – Parameter used to reduce model overconfidence, so that logits / T. Defaults to 1.

  • loss (Optional[LossType]) – Loss function. Defaults to bpr.

  • samplers (List[ItemSampler]) – List of samplers for negative sampling, by default [InBatchSampler()]

Returns

Return type

RetrievalModel