HGN

Reference:

Chen Ma et al. “Hierarchical Gating Networks for Sequential Recommendation.”in SIGKDD 2019

class recbole.model.sequential_recommender.hgn.HGN(config, dataset)[source]

Bases: SequentialRecommender

HGN sets feature gating and instance gating to get the important feature and item for predicting the next item

calculate_loss(interaction)[source]

Calculate the training loss for a batch data.

Parameters:

interaction (Interaction) – Interaction class of the batch.

Returns:

Training loss, shape: []

Return type:

torch.Tensor

feature_gating(seq_item_embedding, user_embedding)[source]

choose the features that will be sent to the next stage(more important feature, more focus)

forward(seq_item, user)[source]

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.

full_sort_predict(interaction)[source]

full sort prediction function. Given users, calculate the scores between users and all candidate items.

Parameters:

interaction (Interaction) – Interaction class of the batch.

Returns:

Predicted scores for given users and all candidate items, shape: [n_batch_users * n_candidate_items]

Return type:

torch.Tensor

instance_gating(user_item, user_embedding)[source]

choose the last click items that will influence the prediction( more important more chance to get attention)

predict(interaction)[source]

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

reg_loss(user_embedding, item_embedding, seq_item_embedding)[source]
training: bool