Fairness
43 techniques
Ensuring AI systems treat different groups and individuals equitably.
Browse by subcategory
All techniques
43 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| SHapley Additive exPlanations | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | SHAP (SHapley Additive exPlanations) explains one prediction by sharing out the gap between that prediction and a... | ||
| Integrated Gradients | Algorithmic | Architecture/neural Networks Architecture/neural Networks/transformer +4 | Image Tabular Text | Integrated Gradients assigns input features scores for a prediction relative to a chosen reference input, called the... | ||
| Gradient Saliency | Algorithmic | Architecture/neural Networks Requirements/differentiable +2 | Image | Gradient saliency (also called vanilla gradient saliency) is the simplest gradient-based explanation for image... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +3 | Image | Grad-CAM (Gradient-weighted Class Activation Mapping) draws a heatmap over an image showing which regions most raise a... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +5 | Any | Influence functions estimate which training examples most affected a model's prediction on a particular test example.... | ||
| Permutation Tests | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | A permutation test asks how likely an observed result would be if there were no real relationship in the data. The... | ||
| 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... | ||
| Statistical Oversampling Methods | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Statistical oversampling methods rebalance a training set by adding synthetic examples of an under-represented category... | ||
| Conformal Prediction | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Conformal prediction wraps any trained model so that, instead of a single answer, it returns a set of plausible answers... | ||
| Bootstrap Ensembles | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Bootstrap ensembles estimate how much a model's predictions depend on the particular sample of data it was trained on.... | ||
| Red Teaming | Process | Architecture/model Agnostic Requirements/black Box | Any | Red teaming is a structured exercise in which a team deliberately tries to make an AI system fail, so that weaknesses... | ||
| 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... | ||
| Concept Activation Vectors | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | A concept activation vector (CAV) is a direction inside a neural network that stands for a human idea such as 'stripes'.... | ||
| 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... |
Rows per page
Page 1 of 3