aif360.sklearn.inprocessing
.AdversarialDebiasing¶

class
aif360.sklearn.inprocessing.
AdversarialDebiasing
(prot_attr=None, scope_name='classifier', adversary_loss_weight=0.1, num_epochs=50, batch_size=128, classifier_num_hidden_units=200, debias=True, verbose=False, random_state=None)[source]¶ Debiasing with adversarial learning.
Adversarial debiasing is an inprocessing technique that learns a classifier to maximize prediction accuracy and simultaneously reduce an adversary’s ability to determine the protected attribute from the predictions [1]. This approach leads to a fair classifier as the predictions cannot carry any group discrimination information that the adversary can exploit.
References
[1] B. H. Zhang, B. Lemoine, and M. Mitchell, “Mitigating Unwanted Biases with Adversarial Learning,” AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, 2018. Variables:  prot_attr (str or list(str)) – Protected attribute(s) used for debiasing.
 groups (array, shape (n_groups,)) – A list of group labels known to the classifier.
 classes (array, shape (n_classes,)) – A list of class labels known to the classifier.
 sess (tensorflow.Session) – The TensorFlow Session used for the
computations. Note: this can be manually closed to free up resources
with
self.sess_.close()
.  classifier_logits (tensorflow.Tensor) – Tensor containing output logits from the classifier.
 adversary_logits (tensorflow.Tensor) – Tensor containing output logits from the adversary.
Parameters:  prot_attr (single label or listlike, optional) – Protected
attribute(s) to use in the debiasing process. If more than one
attribute, all combinations of values (intersections) are
considered. Default is
None
meaning all protected attributes from the dataset are used.  scope_name (str, optional) – TensorFlow “variable_scope” name for the entire model (classifier and adversary).
 adversary_loss_weight (float or
None
, optional) – IfNone
, this will use the suggestion from the paper: \(\alpha = \sqrt(global_step)\) with inverse time decay on the learning rate. Otherwise, it uses the provided coefficient with exponential learning rate decay.  num_epochs (int, optional) – Number of epochs for which to train.
 batch_size (int, optional) – Size of minibatch for training.
 classifier_num_hidden_units (int, optional) – Number of hidden units in the classifier.
 debias (bool, optional) – If
False
, learn a classifier without an adversary.  verbose (bool, optional) – If
True
, print losses every 200 steps.  random_state (int or numpy.RandomState, optional) – Seed of pseudo random number generator for shuffling data and seeding weights.
Methods
decision_function
Soft prediction scores. fit
Train the classifier and adversary (if debias == True
) with the given training data.get_params
Get parameters for this estimator. predict
Predict class labels for the given samples. predict_proba
Probability estimates. score
Return the mean accuracy on the given test data and labels. set_params
Set the parameters of this estimator. 
__init__
(prot_attr=None, scope_name='classifier', adversary_loss_weight=0.1, num_epochs=50, batch_size=128, classifier_num_hidden_units=200, debias=True, verbose=False, random_state=None)[source]¶ Parameters:  prot_attr (single label or listlike, optional) – Protected
attribute(s) to use in the debiasing process. If more than one
attribute, all combinations of values (intersections) are
considered. Default is
None
meaning all protected attributes from the dataset are used.  scope_name (str, optional) – TensorFlow “variable_scope” name for the entire model (classifier and adversary).
 adversary_loss_weight (float or
None
, optional) – IfNone
, this will use the suggestion from the paper: \(\alpha = \sqrt(global_step)\) with inverse time decay on the learning rate. Otherwise, it uses the provided coefficient with exponential learning rate decay.  num_epochs (int, optional) – Number of epochs for which to train.
 batch_size (int, optional) – Size of minibatch for training.
 classifier_num_hidden_units (int, optional) – Number of hidden units in the classifier.
 debias (bool, optional) – If
False
, learn a classifier without an adversary.  verbose (bool, optional) – If
True
, print losses every 200 steps.  random_state (int or numpy.RandomState, optional) – Seed of pseudo random number generator for shuffling data and seeding weights.
 prot_attr (single label or listlike, optional) – Protected
attribute(s) to use in the debiasing process. If more than one
attribute, all combinations of values (intersections) are
considered. Default is

decision_function
(X)[source]¶ Soft prediction scores.
Parameters: X (pandas.DataFrame) – Test samples. Returns: numpy.ndarray – Confidence scores per (sample, class) combination. In the binary case, confidence score for self.classes_[1]
where >0 means this class would be predicted.

fit
(X, y)[source]¶ Train the classifier and adversary (if
debias == True
) with the given training data.Parameters:  X (pandas.DataFrame) – Training samples.
 y (arraylike) – Training labels.
Returns: self

predict
(X)[source]¶ Predict class labels for the given samples.
Parameters: X (pandas.DataFrame) – Test samples. Returns: numpy.ndarray – Predicted class label per sample.

predict_proba
(X)[source]¶ Probability estimates.
The returned estimates for all classes are ordered by the label of classes.
Parameters: X (pandas.DataFrame) – Test samples. Returns: numpy.ndarray – Returns the probability of the sample for each class in the model, where classes are ordered as they are in self.classes_
.