IdEmbeddingsItemNet

class rectools.models.nn.item_net.IdEmbeddingsItemNet(n_factors: int, n_items: int, dropout_rate: float, **kwargs: Any)[source]

Bases: ItemNetBase

Network for item embeddings based only on item ids.

Parameters

  • n_factors (int) – Latent embedding size of item embeddings.

  • n_items (int) – Number of items in the dataset.

  • dropout_rate (float) – Probability of a hidden unit to be zeroed.

  • kwargs (Any) –

Methods

forward(items)

Forward pass to get item embeddings from item ids.

from_dataset(dataset, n_factors, ...)

Create IdEmbeddingsItemNet from RecTools dataset.

from_dataset_schema(dataset_schema, ...)

Construct ItemNet from Dataset schema.

Attributes

out_dim

Return item embedding output dimension.
forward(items: Tensor) → Tensor[source]

Forward pass to get item embeddings from item ids.

Parameters

items (torch.Tensor) – Internal item ids.

Returns

Item embeddings.

Return type

torch.Tensor

classmethod from_dataset(dataset: Dataset, n_factors: int, dropout_rate: float, **kwargs: Any) → Self[source]

Create IdEmbeddingsItemNet from RecTools dataset.

Parameters

  • dataset (Dataset) – RecTools dataset.

  • n_factors (int) – Latent embedding size of item embeddings.

  • dropout_rate (float) – Probability of a hidden unit of item embedding to be zeroed.

  • kwargs (Any) –

Return type

Self

classmethod from_dataset_schema(dataset_schema: DatasetSchema, n_factors: int, dropout_rate: float, **kwargs: Any) → Self[source]

Construct ItemNet from Dataset schema.

Parameters

  • dataset_schema (DatasetSchema) – RecTools schema for dataset.

  • n_factors (int) – Latent embedding size of item embeddings.

  • dropout_rate (float) – Probability of a hidden unit of item embedding to be zeroed.

  • kwargs (Any) –

Return type

Self

property out_dim: int

Return item embedding output dimension.