AFM¶
- Reference:
Jun Xiao et al. “Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks” in IJCAI 2017.
- class recbole.model.context_aware_recommender.afm.AFM(config, dataset)[source]¶
Bases:
recbole.model.abstract_recommender.ContextRecommenderAFM is a attention based FM model that predict the final score with the attention of input feature.
- afm_layer(infeature)[source]¶
Get the attention-based feature interaction score
- Parameters
infeature (torch.FloatTensor) – input feature embedding tensor. shape of [batch_size, field_size, embed_dim].
- Returns
Result of score. shape of [batch_size, 1].
- Return type
torch.FloatTensor
- build_cross(feat_emb)[source]¶
Build the cross feature columns of feature columns
- Parameters
feat_emb (torch.FloatTensor) – input feature embedding tensor. shape of [batch_size, field_size, embed_dim].
- Returns
torch.FloatTensor: Left part of the cross feature. shape of [batch_size, num_pairs, emb_dim].
torch.FloatTensor: Right part of the cross feature. shape of [batch_size, num_pairs, emb_dim].
- Return type
tuple
- 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
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- 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¶