Individual Fairness Guarantees for Neural Networks

05/11/2022
by   Elias Benussi, et al.
0

We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the ϵ-δ-IF formulation, which, given a NN and a similarity metric learnt from data, requires that the output difference between any pair of ϵ-similar individuals is bounded by a maximum decision tolerance δ≥ 0. Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN's non-linearities globally over the input space. We encode this computation as the solution of a Mixed-Integer Linear Programming problem and demonstrate that it can be used to compute IF guarantees on four datasets widely used for fairness benchmarking. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.

READ FULL TEXT

page 5

page 11

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
01/30/2021

Fairness through Optimization

We propose optimization as a general paradigm for formalizing fairness i...
research
12/08/2022

Fairify: Fairness Verification of Neural Networks

Fairness of machine learning (ML) software has become a major concern in...
research
09/28/2021

Local Repair of Neural Networks Using Optimization

In this paper, we propose a framework to repair a pre-trained feed-forwa...
research
06/21/2020

Verifying Individual Fairness in Machine Learning Models

We consider the problem of whether a given decision model, working with ...
research
09/10/2021

Neural Networks for Latent Budget Analysis of Compositional Data

Compositional data are non-negative data collected in a rectangular matr...

Please sign up or login with your details

Forgot password? Click here to reset