NSSALoss¶

class NSSALoss(margin=9.0, adversarial_temperature=1.0, reduction='mean')[source]¶

An implementation of the self-adversarial negative sampling loss function proposed by [sun2019].

Initialize the NSSA loss.

Parameters

margin (float) – The loss’s margin (also written as gamma in the reference paper)
adversarial_temperature (float) – The negative sampling temperature (also written as alpha in the reference paper)
reduction (str) – The name of the reduction operation to aggregate the individual loss values from a batch to a scalar loss value. From {‘mean’, ‘sum’}.

Note

The default hyperparameters are based the experiments for FB15K-237 in [sun2019].

Attributes Summary

`hpo_default`	The default strategy for optimizing the model’s hyper-parameters
`synonyms`

Methods Summary

forward(pos_scores, neg_scores)

Calculate the loss for the given scores.

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'adversarial_temperature': {'high': 1.0, 'low': 0.5, 'type': <class 'float'>}, 'margin': {'high': 30, 'low': 3, 'q': 3, 'type': <class 'int'>}}¶: The default strategy for optimizing the model’s hyper-parameters

synonyms: ClassVar[Optional[Set[str]]] = {'Negative Sampling Self-Adversarial Loss', 'Self-Adversarial Negative Sampling Loss'}¶

Methods Documentation

forward(pos_scores, neg_scores)[source]¶

Calculate the loss for the given scores.