aif360 (version 0.1.0)

adversarial_debiasing: Adversarial Debiasing

Description

Adversarial debiasing is an in-processing technique that learns a classifier to maximize prediction accuracy and simultaneously reduce an adversary's ability to determine the protected attribute from the predictions

Usage

adversarial_debiasing(
  unprivileged_groups,
  privileged_groups,
  scope_name = "current",
  sess = tf$compat$v1$Session(),
  seed = NULL,
  adversary_loss_weight = 0.1,
  num_epochs = 50,
  batch_size = 128,
  classifier_num_hidden_units = 200,
  debias = TRUE
)

Arguments

unprivileged_groups

a list with two values: the column of the protected class and the value indicating representation for unprivileged group

privileged_groups

a list with two values: the column of the protected class and the value indicating representation for privileged group

scope_name

scope name for the tensorflow variables

sess

tensorflow session

seed

seed to make `predict` repeatable.

adversary_loss_weight

hyperparameter that chooses the strength of the adversarial loss.

num_epochs

number of training epochs.

batch_size

batch size.

classifier_num_hidden_units

number of hidden units in the classifier model.

debias

learn a classifier with or without debiasing.

Examples

# NOT RUN {
load_aif360_lib()
ad <- adult_dataset()
p <- list("race", 1)
u <- list("race", 0)

sess = tf$compat$v1$Session()

plain_model = adversarial_debiasing(privileged_groups = p,
                                    unprivileged_groups = u,
                                    scope_name='plain_classifier',
                                    debias=FALSE,
                                    sess=sess)

plain_model$fit(ad)
ad_nodebiasing <- plain_model$predict(ad)
# }