wefe.debias.multiclass_hard_debias.MulticlassHardDebias

class wefe.debias.multiclass_hard_debias.MulticlassHardDebias(pca_args: dict[str, Any] = {'n_components': 10}, verbose: bool = False, criterion_name: str | None = None)[source]

Bases: BaseDebias

Generalized version of Hard Debias that enables multiclass debiasing.

Generalized refers to the fact that this method extends Hard Debias in order to support more than two types of social target sets within the definitional set. For example, for the case of religion bias, it supports a debias using words associated with Christianity, Islam and Judaism.

Examples

Note

For more information on the use of mitigation methods, visit Bias Mitigation (Debias) in the User Guide.

The following example shows how to run an ethnicity debias based on Black, Asian and Caucasian groups.

>>> from wefe.datasets import fetch_debias_multiclass, load_weat
>>> from wefe.debias.multiclass_hard_debias import MulticlassHardDebias
>>> from wefe.utils import load_test_model
>>>
>>> model = load_test_model()  # load a reduced version of word2vec
>>>
>>> # obtain the sets of words that will be used in the debias process.
>>> multiclass_debias_wordsets = fetch_debias_multiclass()
>>> weat_wordsets = load_weat()
>>>
>>> ethnicity_definitional_sets = (
...     multiclass_debias_wordsets["ethnicity_definitional_sets"]
... )
>>> ethnicity_equalize_sets = list(
...     multiclass_debias_wordsets["ethnicity_analogy_templates"].values()
... )
>>>
>>> # instance the debias object that will perform the mitigation
>>> mhd = MulticlassHardDebias(verbose=False, criterion_name="ethnicity")
>>> # fits the transformation parameters (bias direction, etc...)
>>> mhd.fit(
...     model=model,
...     definitional_sets=ethnicity_definitional_sets,
...     equalize_sets=ethnicity_equalize_sets,
... )
>>>
>>> # perform the transformation (debiasing) on the embedding model
>>> ethnicity_debiased_model = mhd.transform(model, copy=True)

References

[1]: Manzini, T., Chong, L. Y., Black, A. W., & Tsvetkov, Y. (2019, June).
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass
Bias in Word Embeddings.
In Proceedings of the 2019 Conference of the North American Chapter of the
Association for Computational Linguistics: Human Language Technologies,
Volume 1 (Long and Short Papers) (pp. 615-621).
[2]: https://github.com/TManzini/DebiasMulticlassWordEmbedding
__init__(pca_args: dict[str, Any] = {'n_components': 10}, verbose: bool = False, criterion_name: str | None = None) → None[source]

Initialize a Multiclass Hard Debias instance.

Parameters:

  • pca_args (Dict[str, Any], optional) – Arguments for the PCA that is calculated internally in the identification of the bias subspace, by default {“n_components”: 10}

  • verbose (bool, optional) – True will print informative messages about the debiasing process, by default False.

  • criterion_name (Optional[str], optional) – The name of the criterion for which the debias is being executed, e.g. ‘Gender’. This will indicate the name of the model returning transform, by default None

fit(model: WordEmbeddingModel, definitional_sets: list[list[str]], equalize_sets: list[list[str]]) → BaseDebias[source]

Compute the bias direction and obtains the equalize embedding pairs.

Parameters:

  • model (WordEmbeddingModel) – The word embedding model to debias.

  • definitional_sets (List[List[str]]) – A sequence of string pairs that will be used to define the bias direction. For example, for the case of gender debias, this list could be [[‘woman’, ‘man’], [‘girl’, ‘boy’], [‘she’, ‘he’], [‘mother’, ‘father’], …]. Multiclass hard debias also accepts lists of sets of more than two words, such as religion where sets of words representing Christianity, Islam and Judaism can be used. See the example for more information.

  • equalize_pairs (Optional[List[List[str]]], optional) – A list with pairs of strings, which will be equalized. In the case of passing None, the equalization will be done over the word pairs passed in definitional_sets, by default None.

Returns:

The debias method fitted.

Return type:

BaseDebias

fit_transform(model: WordEmbeddingModel, target: list[str] | None = None, ignore: list[str] | None = None, copy: bool = True, **fit_params) → WordEmbeddingModel

Convenience method to execute fit and transform in a single call.

Parameters:

  • model (WordEmbeddingModel) – A word embedding model object.

  • target (Optional[List[str]], optional) – If a set of words is specified in target, the debias method will be applied only on the word embeddings of this set, by default None.

  • ignore (Optional[List[str]], optional) – If target is None and a set of words is specified in ignore, the debias method will debias all words except those specified in ignore, by default None.

  • copy (bool, optional) – If True, the debias will be performed on a copy of the model. If False, the debias will be applied on the same model delivered, causing its vectors to mutate. WARNING: Setting copy with True requires at least 2x RAM of the size of the model. Otherwise the execution of the debias may raise MemoryError, by default True.

  • verbose (bool, optional) – True will print informative messages about the debiasing process, by default True.

Returns:

The debiased word embedding model.

Return type:

WordEmbeddingModel

get_metadata_routing()

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routing – A MetadataRequest encapsulating routing information.

Return type:

MetadataRequest

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deep (bool, default=True) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

params – Parameter names mapped to their values.

Return type:

dict

name: str
set_fit_request(*, definitional_sets: bool | None | str = '$UNCHANGED$', equalize_sets: bool | None | str = '$UNCHANGED$', model: bool | None | str = '$UNCHANGED$') → MulticlassHardDebias

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to fit.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

  • definitional_sets (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for definitional_sets parameter in fit.

  • equalize_sets (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for equalize_sets parameter in fit.

  • model (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for model parameter in fit.

Returns:

self – The updated object.

Return type:

object

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**params (dict) – Estimator parameters.

Returns:

self – Estimator instance.

Return type:

estimator instance

set_transform_request(*, copy: bool | None | str = '$UNCHANGED$', ignore: bool | None | str = '$UNCHANGED$', model: bool | None | str = '$UNCHANGED$', target: bool | None | str = '$UNCHANGED$') → MulticlassHardDebias

Configure whether metadata should be requested to be passed to the transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to transform.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

  • copy (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for copy parameter in transform.

  • ignore (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for ignore parameter in transform.

  • model (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for model parameter in transform.

  • target (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for target parameter in transform.

Returns:

self – The updated object.

Return type:

object

transform(model: WordEmbeddingModel, target: list[str] | None = None, ignore: list[str] | None = None, copy: bool = True) → WordEmbeddingModel[source]

Execute Multiclass Hard Debias over the provided model.

Parameters:

  • model (WordEmbeddingModel) – The word embedding model to debias.

  • target (Optional[List[str]], optional) – If a set of words is specified in target, the debias method will be performed only on the word embeddings of this set. If None is provided, the debias will be performed on all words (except those specified in ignore). Note that some words that are not in target may be modified due to the equalization process. by default None.

  • ignore (Optional[List[str]], optional) – If target is None and a set of words is specified in ignore, the debias method will perform the debias in all words except those specified in this set. Note that some words that are in ignore may be modified due to the equalization process. by default None.

  • copy (bool, optional) – If True, the debias will be performed on a copy of the model. If False, the debias will be applied on the same model delivered, causing its vectors to mutate. WARNING: Setting copy with True requires RAM at least 2x of the size of the model, otherwise the execution of the debias may raise to MemoryError, by default True.

Returns:

The debiased embedding model.

Return type:

WordEmbeddingModel