NeuMF

Reference:

Xiangnan He et al. “Neural Collaborative Filtering.” in WWW 2017.

class recbole.model.general_recommender.neumf.NeuMF(config, dataset)

Bases: recbole.model.abstract_recommender.GeneralRecommender

NeuMF is an neural network enhanced matrix factorization model. It replace the dot product to mlp for a more precise user-item interaction.

Note

Our implementation only contains a rough pretraining function.

calculate_loss(interaction)

Calculate the training loss for a batch data.

Parameters

interaction (Interaction) – Interaction class of the batch.

Returns

Training loss, shape: []

Return type

torch.Tensor

dump_parameters()

A simple implementation of dumping model parameters for pretrain.

forward(user, item)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

input_type = 1

load_pretrain()

A simple implementation of loading pretrained parameters.

predict(interaction)

Predict the scores between users and items.

Parameters

interaction (Interaction) – Interaction class of the batch.

Returns

Predicted scores for given users and items, shape: [batch_size]

Return type

torch.Tensor