FwFM

Reference:

Junwei Pan et al. “Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising.” in WWW 2018.

class recbole.model.context_aware_recommender.fwfm.FwFM(config, dataset)[source]

Bases: recbole.model.abstract_recommender.ContextRecommender

FwFM is a context-based recommendation model. It aims to model the different feature interactions between different fields in a much more memory-efficient way. It proposes a field pair weight matrix \(r_{F(i),F(j)}\), to capture the heterogeneity of field pair interactions.

The model defines as follows:

\[y = w_0 + \sum_{i=1}^{m}x_{i}w_{i} + \sum_{i=1}^{m}\sum_{j=i+1}^{m}x_{i}x_{j}<v_{i}, v_{j}>r_{F(i),F(j)}\]
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

forward(interaction)[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.

fwfm_layer(infeature)[source]

Get the field pair weight matrix r_{F(i),F(j)}, and model the different interaction strengths of different field pairs \(\sum_{i=1}^{m}\sum_{j=i+1}^{m}x_{i}x_{j}<v_{i}, v_{j}>r_{F(i),F(j)}\).

Parameters

infeature (torch.cuda.FloatTensor) – [batch_size, field_size, embed_dim]

Returns

[batch_size, 1]

Return type

torch.cuda.FloatTensor

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

training: bool