Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness

by   Samuel Yeom, et al.
Carnegie Mellon University

We turn the definition of individual fairness on its head—rather than ascertaining the fairness of a model given a predetermined metric, we find a metric for a given model that satisfies individual fairness. This can facilitate the discussion on the fairness of a model, addressing the issue that it may be difficult to specify a priori a suitable metric. Our contributions are twofold: First, we introduce the definition of a minimal metric and characterize the behavior of models in terms of minimal metrics. Second, for more complicated models, we apply the mechanism of randomized smoothing from adversarial robustness to make them individually fair under a given weighted L^p metric. Our experiments show that adapting the minimal metrics of linear models to more complicated neural networks can lead to meaningful and interpretable fairness guarantees at little cost to utility.


Individual Fairness in Bayesian Neural Networks

We study Individual Fairness (IF) for Bayesian neural networks (BNNs). S...

Two Simple Ways to Learn Individual Fairness Metrics from Data

Individual fairness is an intuitive definition of algorithmic fairness t...

Metric Learning for Individual Fairness

There has been much discussion recently about how fairness should be mea...

Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework

Machine learning is widely used to make decisions with societal impact s...

Verifying Individual Fairness in Machine Learning Models

We consider the problem of whether a given decision model, working with ...

Leave-one-out Unfairness

We introduce leave-one-out unfairness, which characterizes how likely a ...

An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision

The notion of individual fairness requires that similar people receive s...

Please sign up or login with your details

Forgot password? Click here to reset