A Differentiable Distance Approximation for Fairer Image Classification

10/09/2022
by   Nicholas Rosa, et al.
0

Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the cost of extra computation, unstable adversarial optimisation or have losses on the feature space structure that are disconnected from fairness measures and only loosely generalise to fairness. In this work we propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model. Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training and directly improves the fairness of the regularised models. We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios, whilst still maintaining a high level of classification accuracy. Code is available at https://bitbucket.org/nelliottrosa/base_fairness.

READ FULL TEXT
research
03/15/2022

Distraction is All You Need for Fairness

With the recent growth in artificial intelligence models and its expandi...
research
02/24/2023

Intersectional Fairness: A Fractal Approach

The issue of fairness in AI has received an increasing amount of attenti...
research
05/05/2022

Optimising Equal Opportunity Fairness in Model Training

Real-world datasets often encode stereotypes and societal biases. Such b...
research
04/26/2020

Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds

Most NLP datasets are not annotated with protected attributes such as ge...
research
12/01/2020

FairFaceGAN: Fairness-aware Facial Image-to-Image Translation

In this paper, we introduce FairFaceGAN, a fairness-aware facial Image-t...
research
09/24/2021

On the Fairness of Swarm Learning in Skin Lesion Classification

in healthcare. However, the existing AI model may be biased in its decis...

Please sign up or login with your details

Forgot password? Click here to reset