Minimax Pareto Fairness: A Multi Objective Perspective

by   Natalia Martinez, et al.

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.



page 1

page 2

page 3

page 4


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

Common fairness definitions in machine learning focus on balancing notio...

Convergent Algorithms for (Relaxed) Minimax Fairness

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

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

The goal of fairness in classification is to learn a classifier that doe...

Multi-Differential Fairness Auditor for Black Box Classifiers

Machine learning algorithms are increasingly involved in sensitive decis...

Exchanging Lessons Between Algorithmic Fairness and Domain Generalization

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

Group-Fairness in Influence Maximization

Influence maximization is a widely used model for information disseminat...

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.