Agnostic data debiasing through a local sanitizer learnt from an adversarial network approach

06/19/2019
by   Ulrich Aïvodji, et al.
0

The widespread use of automated decision processes in many areas of our society raises serious ethical issues concerning the fairness of the process and the possible resulting discriminations. In this work, we propose a novel approach called whose objective is to prevent the possibility of any discrimination i.e., direct and indirect) based on a sensitive attribute by removing the attribute itself as well as the existing correlations with the remaining attributes. Our sanitization algorithm is partially inspired by the powerful framework of generative adversarial networks (in particuler the Cycle-GANs), which offers a flexible way to learn a distribution empirically or to translate between two different distributions. In contrast to prior work, one of the strengths of our approach is that the sanitization is performed in the same space as the original data by only modifying the other attributes as little as possible and thus preserving the interpretability of the sanitized data. As a consequence, once the sanitizer is trained, it can be applied to new data, such as for instance, locally by an individual on his profile before releasing it. Finally, experiments on a real dataset demonstrate the effectiveness of the proposed approach as well as the achievable trade-off between fairness and utility.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2018

FairGAN: Fairness-aware Generative Adversarial Networks

Fairness-aware learning is increasingly important in data mining. Discri...
research
09/01/2022

Fair mapping

To mitigate the effects of undesired biases in models, several approache...
research
05/14/2020

Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning

Machine learning is being integrated into a growing number of critical s...
research
08/25/2020

Local Generalization and Bucketization Technique for Personalized Privacy Preservation

Anonymization technique has been extensively studied and widely applied ...
research
10/12/2022

Fairness via Adversarial Attribute Neighbourhood Robust Learning

Improving fairness between privileged and less-privileged sensitive attr...
research
06/11/2023

Toward Fair Facial Expression Recognition with Improved Distribution Alignment

We present a novel approach to mitigate bias in facial expression recogn...
research
03/11/2022

Reprogramming FairGANs with Variational Auto-Encoders: A New Transfer Learning Model

Fairness-aware GANs (FairGANs) exploit the mechanisms of Generative Adve...

Please sign up or login with your details

Forgot password? Click here to reset