Optimal Transport for Fairness

[2202.03814] Optimal Transport of Classifiers to Fairness - arXiv

We introduce Optimal Transport to Fairness (OTF), a method that quantifies the violation of fairness constraints as the smallest Optimal Transport cost.

Optimal Transport of Classifiers to Fairness - NIPS papers

We propose to quantify the unfairness of a probabilistic classifier as the Optimal Transport to Fairness (OTF) cost, which is defined as the smallest OT cost ...

A General Approach to Fairness with Optimal Transport

We use optimal transport theory to derive target distributions and methods that allow us to achieve fairness with minimal changes to the unfair model. Our ...

Obtaining Fairness using Optimal Transport Theory

Abstract. In the fair classification setup, we recast the links between fairness and predictability in terms of probability metrics. We analyze repair methods ...

Optimal Transport for Fairness: Archival Data Repair using ... - arXiv

In this paper, we define fairness in terms of conditional independence between protected attributes (S) and features (X), given unprotected attributes (U).

Optimal transport of classifiers to fairness - ACM Digital Library

To validate this hypothesis, we introduce Optimal Transport to Fairness (OTF), a method that quantifies the violation of fairness constraints as ...

A General Approach to Fairness with Optimal Transport

Abstract. We propose a general approach to fairness based on transporting distributions corresponding to different sensitive attributes to a ...

Obtaining fairness using optimal transport theory - HAL

Statistical algorithms are usually helping in making decisions in many aspects of our lives. But, how do we know if these algorithms are biased and commit ...

aida-ugent/OTF: Optimal Transport of Classifiers to Fairness ...

Optimal Transport to Fairness (OTF). This project contains an accessible implementation of the OTF cost function proposed in the paper Optimal Transport of ...

Everything is Relative: Understanding Fairness with Optimal Transport

This work uses the optimal transport map to examine individual, subgroup, and group fairness and presents an optimal transport-based approach to fairness ...

ICML Poster Testing Group Fairness via Optimal Transport Projections

The proposed framework can also be used to test for composite fairness hypotheses and fairness with multiple sensitive attributes. The optimal transport testing ...

Testing Group Fairness via Optimal Transport Projections

The proposed framework can also be used to test for testing composite fairness hy- potheses and fairness with multiple sensitive at- tributes. The optimal ...

Obtaining Fairness using Optimal Transport Theory

Obtaining Fairness using. Optimal Transport Theory. Authors: Eustasio del Barrio, Fabrice Gamboa, Paula. Gordaliza , Jean-Michel Loubes. Presenter: Theo Hu ...

Optimal Transport of Classifiers to Fairness - OpenReview

To validate this hypothesis, we introduce Optimal Transport to Fairness (OTF), a method that quantifies the violation of fairness constraints as ...

Fairness in Machine Learning via Optimal Transport - eScholarship

Fairness in Machine Learning via Optimal Transport ... As machine learning powered decision-making becomes increasingly important in our daily lives, it is ...

Everything is Relative: Understanding Fairness with Optimal Transport

We present an optimal transport-based approach to fairness that offers an interpretable and quantifiable exploration of bias and its structure by comparing a ...

Fair Learning : an optimal transport based approach - HAL Thèses

The aim of this thesis is two-fold. On the one hand, optimal transportation methods are studied for statistical inference purposes. On the other hand, ...

Fair Learning: an optimal transport based approach

Fair Learning: an optimal transport based approach. Autor: Gordaliza Pastor, Paula. Director o Tutor: Barrio Tellado, Eustasio del Autoridad UVA.

Optimal Transport and its Applications to Fairness - DZone

As fairness in AI becomes an increasing area of focus across industries, data scientists should consider the value of optimal transport ... Having ...

Towards Fairness in Machine Learning via Optimal Transport

We propose a rigorous algorithmic framework for fair data representation based on optimal transport, which allows us to estimate the Pareto ...