class recbole.model.general_recommender.asymknn.AsymKNN(config, dataset)

Bases: GeneralRecommender

AsymKNN: A traditional recommender model based on asymmetric cosine similarity and score prediction.

AsymKNN computes user-item recommendations by leveraging asymmetric cosine similarity over the interaction matrix. This model allows for flexible adjustment of similarity calculations and scoring normalization via several tunable parameters.

Config:

k (int): Number of neighbors to consider in the similarity calculation. method (str): Specifies whether to calculate similarities based on users or items.

Valid options are ‘user’ or ‘item’.

alpha (float): Weight parameter for asymmetric cosine similarity, controlling

the importance of the interaction matrix in the similarity computation. Must be in the range [0, 1].

q (int): Exponent for adjusting the ‘locality of scoring function’ after similarity computation. beta (float): Parameter for controlling the balance between factors in the

final score normalization. Must be in the range [0, 1].

Reference:

Aiolli,F et al. Efficient top-n recommendation for very large scale binary rated datasets. In Proceedings of the 7th ACM conference on Recommender systems (pp. 273-280). ACM.

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

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.

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

input_type = 1

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

training: bool

type = 5

class recbole.model.general_recommender.asymknn.ComputeSimilarity(dataMatrix, topk=100, alpha=0.5, method='item')

Bases: object

compute_asym_similarity(block_size=100)

Compute the asymmetric cosine similarity for the given dataset.

Parameters:

block_size (int) – Divide matrix into blocks for efficient calculation.

Returns:

The similar nodes, if method is ‘user’, the shape is [number of users, neigh_num], else, the shape is [number of items, neigh_num]. scipy.sparse.csr_matrix: sparse matrix W, if method is ‘user’, the shape is [self.n_rows, self.n_rows], else, the shape is [self.n_columns, self.n_columns].

Return type:

list