What is an incompatibility of fairness metrics?
The idea that some notions of fairness are mutually incompatible and cannot be satisfied simultaneously.
incompatibility of fairness metrics explained in plain English
The idea that some notions of fairness are mutually incompatible and cannot be satisfied simultaneously. As a result, there is no single universal metric for quantifying fairness that can be applied to all ML problems. While this may seem discouraging, incompatibility of fairness metrics doesn't imply that fairness efforts are fruitless. Instead, it suggests that fairness must be defined contextually for a given ML problem, with the goal of preventing harms specific to its use cases. See"On the (im)possibility of fairness" for a more detailed discussion of the incompatibility of fairness metrics.
Example
Practitioners refer to incompatibility of fairness metrics when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- bias
1.
- bias (math) or bias term
An intercept or offset from an origin.
- confirmation bias
The tendency to search for, interpret, favor, and recall information in a way that confirms one's pre-existing beliefs or hypotheses.
- counterfactual fairness
A fairness metric that checks whether a classification model produces the same result for one individual as it does for another individual who is identical to the first, except with respect to one or more sensitive attributes.
- demographic parity
A fairness metric that is satisfied if the results of a model's classification are not dependent on a given sensitive attribute.
- discriminative model
A model that predicts labels from a set of one or more features.
- equality of opportunity
A fairness metric to assess whether a model is predicting the desirable outcome equally well for all values of a sensitive attribute.
- equalized odds
A fairness metric to assess whether a model is predicting outcomes equally well for all values of a sensitive attribute with respect to both the positive class and negative class—not just one class or the other exclusively.
- evaluation
The process of measuring a model's quality or comparing different models against each other.
- fairness metric
A mathematical definition of "fairness" that is measurable.