Verifying Individual Fairness in Machine Learning Models

06/21/2020
by   Philips George John, et al.
0

We consider the problem of whether a given decision model, working with structured data, has individual fairness. Following the work of Dwork, a model is individually biased (or unfair) if there is a pair of valid inputs which are close to each other (according to an appropriate metric) but are treated differently by the model (different class label, or large difference in output), and it is unbiased (or fair) if no such pair exists. Our objective is to construct verifiers for proving individual fairness of a given model, and we do so by considering appropriate relaxations of the problem. We construct verifiers which are sound but not complete for linear classifiers, and kernelized polynomial/radial basis function classifiers. We also report the experimental results of evaluating our proposed algorithms on publicly available datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/20/2022

CertiFair: A Framework for Certified Global Fairness of Neural Networks

We consider the problem of whether a Neural Network (NN) model satisfies...
research
04/21/2023

Individual Fairness in Bayesian Neural Networks

We study Individual Fairness (IF) for Bayesian neural networks (BNNs). S...
research
12/20/2020

Biased Models Have Biased Explanations

We study fairness in Machine Learning (FairML) through the lens of attri...
research
02/18/2020

Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness

We turn the definition of individual fairness on its head—rather than as...
research
09/03/2019

Avoiding Resentment Via Monotonic Fairness

Classifiers that achieve demographic balance by explicitly using protect...
research
04/04/2020

Abstracting Fairness: Oracles, Metrics, and Interpretability

It is well understood that classification algorithms, for example, for d...
research
05/11/2022

Individual Fairness Guarantees for Neural Networks

We consider the problem of certifying the individual fairness (IF) of fe...

Please sign up or login with your details

Forgot password? Click here to reset