nsl.lib.virtual_adv_regularizer

Stay organized with collections Save and categorize content based on your preferences.

Calculates virtual adversarial loss for the given input.

Virtual adversarial loss is defined as the distance between the embedding of the input and that of a slightly perturbed input. Optimizing this loss helps smooth models locally.

Reference paper: https://arxiv.org/pdf/1704.03976.pdf

input_layer a dense tensor for input features whose first dimension is the training batch size.
embedding_fn a unary function that computes the embedding for the given input_layer input.
virtual_adv_config an nsl.configs.VirtualAdvConfig object that specifies parameters for generating adversarial examples and computing the adversarial loss.
embedding (optional) a dense tensor representing the embedding of input_layer. If not provided, it will be calculated as embedding_fn(input_layer).

virtual_adv_loss a float32 denoting the virtural adversarial loss.