hopwise.model.general_recommender.ncl¶

Reference:: Zihan Lin*, Changxin Tian*, Yupeng Hou*, Wayne Xin Zhao. “Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning.” in WWW 2022.

Classes¶

NCL

NCL is a neighborhood-enriched contrastive learning paradigm for graph collaborative filtering.

Module Contents¶

class hopwise.model.general_recommender.ncl.NCL(config, dataset)¶

Bases: hopwise.model.abstract_recommender.GeneralRecommender

NCL is a neighborhood-enriched contrastive learning paradigm for graph collaborative filtering. Both structural and semantic neighbors are explicitly captured as contrastive learning objects.

input_type¶

latent_dim¶

n_layers¶

reg_weight¶

ssl_temp¶

ssl_reg¶

hyper_layers¶

alpha¶

proto_reg¶

k¶

user_embedding¶

item_embedding¶

mf_loss¶

reg_loss¶

restore_user_e = None¶

restore_item_e = None¶

norm_adj_matrix¶

other_parameter_name = ['restore_user_e', 'restore_item_e']¶

user_centroids = None¶

user_2cluster = None¶

item_centroids = None¶

item_2cluster = None¶

e_step()¶

run_kmeans(x)¶: Run K-means algorithm to get k clusters of the input tensor x

get_ego_embeddings()¶

Get the embedding of users and items and combine to an embedding matrix.

Returns:: Tensor of the embedding matrix. Shape of [n_items+n_users, embedding_dim]

forward()¶

ProtoNCE_loss(node_embedding, user, item)¶

ssl_layer_loss(current_embedding, previous_embedding, user, item)¶

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

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

full_sort_predict(interaction)¶

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