AdversarialLoss¶
- class AdversarialLoss(inverse_softmax_temperature=1.0, reduction='mean')[source]¶
Bases:
SetwiseLoss
A loss with adversarial weighting of negative samples.
Initialize the adversarial loss.
- Parameters:
Methods Summary
forward
(pos_scores, neg_scores, neg_weights)Calculate the loss for the given scores.
negative_loss_term_unreduced
(neg_scores[, ...])Calculate the loss for the negative scores without reduction.
positive_loss_term
(pos_scores[, ...])Calculate the loss for the positive scores.
process_lcwa_scores
(predictions, labels[, ...])Process scores from LCWA training loop.
process_slcwa_scores
(positive_scores, ...[, ...])Process scores from sLCWA training loop.
Methods Documentation
- forward(pos_scores, neg_scores, neg_weights, label_smoothing=None, num_entities=None)[source]¶
Calculate the loss for the given scores.
- Parameters:
pos_scores (
FloatTensor
) – shape: s_p a tensor of positive scoresneg_scores (
FloatTensor
) – shape: s_n a tensor of negative scoresneg_weights (
FloatTensor
) – shape: s_n the adversarial weights of the negative scoreslabel_smoothing (
Optional
[float
]) – An optional label smoothing parameter.num_entities (
Optional
[int
]) – The number of entities (required for label-smoothing).
- Return type:
FloatTensor
- Returns:
a scalar loss value
- abstract negative_loss_term_unreduced(neg_scores, label_smoothing=None, num_entities=None)[source]¶
Calculate the loss for the negative scores without reduction.
- Parameters:
- Return type:
FloatTensor
- Returns:
scalar the unreduced loss term for negative scores
- abstract positive_loss_term(pos_scores, label_smoothing=None, num_entities=None)[source]¶
Calculate the loss for the positive scores.
- Parameters:
- Return type:
FloatTensor
- Returns:
scalar the reduced loss term for positive scores
- process_lcwa_scores(predictions, labels, label_smoothing=None, num_entities=None)[source]¶
Process scores from LCWA training loop.
- Parameters:
predictions (
FloatTensor
) – shape: (batch_size, num_entities) The scores.labels (
FloatTensor
) – shape: (batch_size, num_entities) The labels.label_smoothing (
Optional
[float
]) – An optional label smoothing parameter.num_entities (
Optional
[int
]) – The number of entities (required for label-smoothing).
- Return type:
FloatTensor
- Returns:
A scalar loss value.
- process_slcwa_scores(positive_scores, negative_scores, label_smoothing=None, batch_filter=None, num_entities=None)[source]¶
Process scores from sLCWA training loop.
- Parameters:
positive_scores (
FloatTensor
) – shape: (batch_size, 1) The scores for positive triples.negative_scores (
FloatTensor
) – shape: (batch_size, num_neg_per_pos) or (num_unfiltered_negatives,) The scores for the negative triples, either in dense 2D shape, or in case they are already filtered, in sparse shape. If they are given in sparse shape, batch_filter needs to be provided, too.label_smoothing (
Optional
[float
]) – An optional label smoothing parameter.batch_filter (
Optional
[BoolTensor
]) – shape: (batch_size, num_neg_per_pos) An optional filter of negative scores which were kept. Given if and only if negative_scores have been pre-filtered.num_entities (
Optional
[int
]) – The number of entities. Only required if label smoothing is enabled.
- Return type:
FloatTensor
- Returns:
A scalar loss term.