Generalized Disparate Impact for Configurable Fairness Solutions in ML

05/29/2023
by   Luca Giuliani, et al.
0

We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.

READ FULL TEXT
research
07/25/2023

An Empirical Study on Fairness Improvement with Multiple Protected Attributes

Existing research mostly improves the fairness of Machine Learning (ML) ...
research
02/24/2023

Intersectional Fairness: A Fractal Approach

The issue of fairness in AI has received an increasing amount of attenti...
research
11/18/2018

Bayesian Modeling of Intersectional Fairness: The Variance of Bias

Intersectionality is a framework that analyzes how interlocking systems ...
research
12/26/2022

Bias Mitigation Framework for Intersectional Subgroups in Neural Networks

We propose a fairness-aware learning framework that mitigates intersecti...
research
06/10/2021

Fair Classification with Adversarial Perturbations

We study fair classification in the presence of an omniscient adversary ...
research
10/15/2018

Neural Styling for Interpretable Fair Representations

We observe a rapid increase in machine learning models for learning data...
research
11/04/2022

Decorrelation with conditional normalizing flows

The sensitivity of many physics analyses can be enhanced by constructing...

Please sign up or login with your details

Forgot password? Click here to reset