data requirements
access to training data
Requires the original training dataset
7 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Influence Functions | Algorithmic | Model Agnostic | Any | Influence functions quantify how much each training example influenced a model's predictions by computing the change in... | ||
| Bootstrapping | Algorithmic | Model Agnostic | Any | Bootstrapping estimates uncertainty by repeatedly resampling the original dataset with replacement to create many new... | ||
| Jackknife Resampling | Algorithmic | Model Agnostic | Any | Jackknife resampling (also called leave-one-out resampling) assesses model stability and uncertainty by systematically... | ||
| Model Cards | Documentation | Model Agnostic | Any | Model cards are standardised documentation frameworks that systematically document machine learning models through... | ||
| Model Distillation | Algorithmic | Neural Network | Any | Model distillation transfers knowledge from a large, complex model (teacher) to a smaller, more efficient model... | ||
| Reweighing | Algorithmic | Model Agnostic | Any | Reweighing is a pre-processing technique that mitigates bias by assigning different weights to training examples based... | ||
| Relabelling | Procedural | Model Agnostic | Any | A preprocessing fairness technique that modifies class labels in training data to achieve equal positive outcome rates... |
Rows per page
Page 1 of 1