applicable models
training data
Requires access to the original training dataset
24 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Prototype and Criticism Models | Algorithmic | Architecture/model Agnostic Paradigm/supervised +3 | Any | Prototype and Criticism Models provide data understanding by identifying two complementary sets of examples: prototypes... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +6 | Any | Influence functions quantify how much each training example influenced a model's predictions by computing the change in... | ||
| RuleFit | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | RuleFit creates interpretable surrogate models that can explain complex black-box models or serve as interpretable... | ||
| Sensitivity Analysis for Fairness | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Sensitivity Analysis for Fairness systematically evaluates how model predictions change when sensitive attributes or... | ||
| Synthetic Data Generation | Algorithmic | Architecture/neural Networks/generative/gan Architecture/neural Networks/generative/vae +5 | Any | Synthetic data generation creates artificial datasets that aim to preserve the statistical properties, distributions,... | ||
| Deep Ensembles | Algorithmic | Architecture/neural Networks Paradigm/parametric +2 | Any | Deep ensembles combine predictions from multiple neural networks trained independently with different random... | ||
| Bootstrapping | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Bootstrapping estimates uncertainty by repeatedly resampling the original dataset with replacement to create many new... | ||
| Jackknife Resampling | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Jackknife resampling (also called leave-one-out resampling) assesses model stability and uncertainty by systematically... | ||
| Cross-validation | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Cross-validation evaluates model performance and robustness by systematically partitioning data into multiple subsets... | ||
| Anomaly Detection | Algorithmic | Architecture/model Agnostic Requirements/black Box +1 | Any | Anomaly detection identifies unusual behaviours, inputs, or outputs that deviate significantly from established normal... | ||
| Model Distillation | Algorithmic | Architecture/neural Networks Paradigm/parametric +3 | Any | Model distillation transfers knowledge from a large, complex model (teacher) to a smaller, more efficient model... | ||
| Reweighing | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Reweighing is a pre-processing technique that mitigates bias by assigning different weights to training examples based... | ||
| Disparate Impact Remover | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Tabular | Disparate Impact Remover is a preprocessing technique that transforms feature values in a dataset to reduce statistical... | ||
| Fairness GAN | Algorithmic | Architecture/neural Networks/generative/gan Paradigm/generative +4 | Any | A data generation technique that employs Generative Adversarial Networks (GANs) to create fair synthetic datasets by... | ||
| Relabelling | Procedural | Architecture/model Agnostic Paradigm/supervised +2 | Any | A preprocessing fairness technique that modifies class labels in training data to achieve equal positive outcome rates... | ||
| Preferential Sampling | Procedural | Architecture/model Agnostic Paradigm/supervised +2 | Any | A preprocessing fairness technique developed by Kamiran and Calders that addresses dataset imbalances by re-sampling... | ||
| Attribute Removal (Fairness Through Unawareness) | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Attribute Removal (Fairness Through Unawareness) ensures fairness by completely excluding protected attributes such as... | ||
| Fair Adversarial Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +6 | Any | An in-processing fairness technique that employs adversarial training with dual neural networks to learn fair... | ||
| Prejudice Remover Regulariser | Algorithmic | Architecture/linear Models/logistic Architecture/probabilistic +5 | Tabular | An in-processing fairness technique that adds a fairness penalty to machine learning models to reduce bias against... | ||
| Exponentiated Gradient Reduction | Algorithmic | Architecture/model Agnostic Paradigm/discriminative +5 | Any | An in-processing fairness technique based on Agarwal et al.'s reductions approach that transforms fair classification... |
Rows per page
Page 1 of 2