Learning fair representation with a parametric integral probability metric

02/07/2022
by   Dongha Kim, et al.
6

As they have a vital effect on social decision-making, AI algorithms should be not only accurate but also fair. Among various algorithms for fairness AI, learning fair representation (LFR), whose goal is to find a fair representation with respect to sensitive variables such as gender and race, has received much attention. For LFR, the adversarial training scheme is popularly employed as is done in the generative adversarial network type algorithms. The choice of a discriminator, however, is done heuristically without justification. In this paper, we propose a new adversarial training scheme for LFR, where the integral probability metric (IPM) with a specific parametric family of discriminators is used. The most notable result of the proposed LFR algorithm is its theoretical guarantee about the fairness of the final prediction model, which has not been considered yet. That is, we derive theoretical relations between the fairness of representation and the fairness of the prediction model built on the top of the representation (i.e., using the representation as the input). Moreover, by numerical experiments, we show that our proposed LFR algorithm is computationally lighter and more stable, and the final prediction model is competitive or superior to other LFR algorithms using more complex discriminators.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/20/2023

Within-group fairness: A guidance for more sound between-group fairness

As they have a vital effect on social decision-making, AI algorithms not...
research
02/07/2022

SLIDE: a surrogate fairness constraint to ensure fairness consistency

As they have a vital effect on social decision makings, AI algorithms sh...
research
01/08/2021

A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness

Motivated by the need for fair algorithmic decision making in the age of...
research
11/15/2020

FAIR: Fair Adversarial Instance Re-weighting

With growing awareness of societal impact of artificial intelligence, fa...
research
03/10/2019

Fair Logistic Regression: An Adversarial Perspective

Fair prediction methods have primarily been built around existing classi...
research
05/10/2021

Joint Fairness Model with Applications to Risk Predictions for Under-represented Populations

Under-representation of certain populations, based on gender, race/ethni...
research
12/11/2020

Fairness in Rating Prediction by Awareness of Verbal and Gesture Quality of Public Speeches

The role of verbal and non-verbal cues towards great public speaking has...

Please sign up or login with your details

Forgot password? Click here to reset