Minimax Pareto Fairness: A Multi Objective Perspective

11/03/2020
by   Natalia Martinez, et al.
5

In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case classification errors between outcomes in unbalanced classification problems. We test the proposed methodology on real case-studies of predicting income, ICU patient mortality, skin lesions classification, and assessing credit risk, demonstrating how our framework compares favorably to other approaches.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

11/16/2019

Fairness With Minimal Harm: A Pareto-Optimal Approach For Healthcare

Common fairness definitions in machine learning focus on balancing notio...
11/05/2020

Convergent Algorithms for (Relaxed) Minimax Fairness

We consider a recently introduced framework in which fairness is measure...
09/09/2020

Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm

The goal of fairness in classification is to learn a classifier that doe...
03/18/2019

Multi-Differential Fairness Auditor for Black Box Classifiers

Machine learning algorithms are increasingly involved in sensitive decis...
10/14/2020

Exchanging Lessons Between Algorithmic Fairness and Domain Generalization

Standard learning approaches are designed to perform well on average for...
03/03/2019

Group-Fairness in Influence Maximization

Influence maximization is a widely used model for information disseminat...
06/08/2020

Achieving Equalized Odds by Resampling Sensitive Attributes

We present a flexible framework for learning predictive models that appr...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.