predict_t_uncertain

predict_t_uncertain(model, hr_batch, num_samples=5, slice_size=None, *, mode=None)[source]

Forward pass using right side (tail) prediction for obtaining scores of all possible tails.

This method calculates the score for all possible tails for each (head, relation) pair, as well as an uncertainty quantification.

Note

We only expect the right side predictions, i.e., \((h,r,*)\) to change its default behavior when the model has been trained with inverse relations (mainly because of the behavior of the LCWA training approach). This is why the predict_h_uncertain() has different behavior depending on if inverse triples were used in training, and why this function has the same behavior regardless of the use of inverse triples.

Parameters
  • model (Model) – the model used for predicting scores

  • hr_batch (LongTensor) – shape: (batch_size, 2) The indices of (head, relation) pairs.

  • slice_size (Optional[int]) – >0 The divisor for the scoring function when using slicing.

  • num_samples (int) – >1 the number of samples to draw

  • mode (Optional[Literal[‘training’, ‘validation’, ‘testing’]]) – The pass mode, which is None in the transductive setting and one of “training”, “validation”, or “testing” in the inductive setting.

Return type

UncertainPrediction

Returns

shape: (batch_size, num_entities) For each h-r pair, the scores for all possible tails.

This function delegates to predict_uncertain_helper() by using pykeen.models.Model.score_t() as the score_method.

Warning

This function sets the model to evaluation mode and all dropout layers to training mode.