Dictionary · Glossary
L2 — definitions grouped by regulatory framework.
Nouns
20 senses- Training Data
A dataset from which a model is learned.
- Transformer
A procedure that modifies a dataset.
- Bias Mitigation Algorithm
A procedure for reducing unwanted bias in training data or models.
- Classifier
A model that predicts categorical labels from features.
- Bias
A systematic error. In the context of fairness, we are concerned with unwanted bias that places privileged groups at systematic advantage and unprivileged groups at systematic disadvantage.
- Score
A continuous value output from a classifier. Applying a threshold to a score results in a predicted label.
- Explainer
Functionality for providing details on or causes for fairness metric results.
- Feature
An attribute containing information for predicting the label.
- Favorable Label
A label whose value corresponds to an outcome that provides an advantage to the recipient. The opposite is an unfavorable label.
- Group Fairness
The goal of groups defined by protected attributes receiving similar treatments or outcomes.
- In-Processing Algorithm
A bias mitigation algorithm that is applied to a model during its training.
- Fairness Metric
A quantification of unwanted bias in training data or models.
- Individual Fairness
The goal of similar individuals receiving similar treatments or outcomes.
- Instance Weight
A numerical value that multiplies the contribution of a data point in a model.
- Label
A value corresponding to an outcome.
- Model
A function that takes features as input and predicts labels as output.
- Protected Attribute
An attribute that partitions a population into groups whose outcomes should have parity. Examples include race, gender, caste, and religion. Protected attributes are not universal, but are application specific.
- Post-Processing Algorithm
A bias mitigation algorithm that is applied to predicted labels.
- Pre-Processing Algorithm
A bias mitigation algorithm that is applied to training data.
- Privileged Protected Attribute
A value of a protected attribute indicating a group that has historically been at systematic advantage.