data requirements
sensitive attributes
Needs data labelled with protected attributes
31 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Demographic Parity Assessment | Metric | Architecture/model Agnostic Paradigm/supervised +1 | Any | Demographic Parity Assessment checks whether a model gives a favourable outcome, such as a loan approval or an interview... | ||
| Adversarial Debiasing | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Adversarial debiasing trains a model so that its predictions carry as little information as possible about a protected... | ||
| Counterfactual Fairness Assessment | Testing | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Counterfactual Fairness Assessment tests whether a model would have made the same predictions for a person had their... | ||
| Causal Discrimination Testing | Testing | Architecture/model Agnostic Paradigm/supervised +1 | Tabular Text | Causal discrimination testing checks whether a system gives different outputs to otherwise identical inputs because of a... | ||
| Model Cards | Documentation | Architecture/model Agnostic Requirements/black Box | Any | A model card is a short structured document published with a trained model, stating what the model is for and what it... | ||
| Reweighing | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Reweighing is a fairness method, presented by Kamiran and Calders (2012), that adjusts the training data before any... | ||
| Disparate Impact Remover | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Disparate Impact Remover is a pre-processing method that edits the numerical features of a dataset so that they reveal... | ||
| Fairness GAN | Algorithmic | Architecture/neural Networks/generative/gan Paradigm/generative +3 | Any | Fairness GAN is a pre-processing method that generates a synthetic training dataset in which decisions no longer track a... | ||
| Relabelling | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Relabelling, also called data massaging, is a pre-processing method proposed by Kamiran and Calders. It changes some of... | ||
| Preferential Sampling | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Preferential Sampling is a pre-processing method, proposed by Kamiran and Calders, that rebalances a training set so... | ||
| Attribute Removal (Fairness Through Unawareness) | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Attribute removal, also called fairness through unawareness, trains and runs a model without the protected attributes,... | ||
| Fair Adversarial Networks | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Fair Adversarial Networks is a pre-processing method, proposed by Cevora (2020), that rewrites a dataset so that a... | ||
| Prejudice Remover Regulariser | Algorithmic | Architecture/linear Models/logistic Architecture/probabilistic +4 | Tabular | The Prejudice Remover Regulariser, proposed by Kamishima and colleagues (2012), trains a classifier with an extra... | ||
| Meta Fair Classifier | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | The meta fair classifier is a general-purpose training algorithm for fair classification. The user chooses a fairness... | ||
| Exponentiated Gradient Reduction | Algorithmic | Architecture/model Agnostic Paradigm/discriminative +4 | Any | Exponentiated gradient reduction trains a classifier that satisfies a chosen fairness criterion, such as demographic... | ||
| Learning Adversarially Fair and Transferable Representations | Algorithmic | Architecture/neural Networks Paradigm/parametric +4 | Image Tabular | Learning Adversarially Fair and Transferable Representations (LAFTR) trains an encoder that turns each record into a... | ||
| Multi-Accuracy Boosting | Algorithmic | Architecture/ensemble Paradigm/discriminative +2 | Any | Multi-accuracy boosting is a post-processing method that corrects a trained classifier's systematic errors on subgroups... | ||
| Threshold Optimiser | Algorithmic | Architecture/model Agnostic Paradigm/discriminative +2 | Any | Threshold Optimiser is a post-processing method, introduced by Hardt, Price and Srebro (2016), that adjusts a trained... | ||
| Reject Option Classification | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Reject Option Classification is a post-processing method, proposed by Kamiran and colleagues (2012), that changes some... | ||
| Calibration with Equality of Opportunity | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Calibration with equality of opportunity is a post-processing step that adjusts a classifier's scores so that two groups... |
Rows per page
Page 1 of 2