<  Back to the Polytechnique Montréal portal

Generative adversarial networks for mitigating biases in machine learning systems

Adel Abusitta, Esma Aïmeur and Omar Abdul Wahab

Paper (2020)

Open Acess document at official publisher

Document published while its authors were not affiliated with Polytechnique Montréal

An external link is available for this item
Show abstract
Hide abstract

Abstract

In this paper, we propose a new framework for mitigating biases in machine learning systems. The problem of the existin gmitigation approaches is that they are model-oriented in the sense that they focus on tuning the training algorithms to produce fair results, while overlooking the fact that the training data can itself be the main reason for biased outcomes. Technically speaking, two essential limitations can be found in such model-based approaches: 1)the mitigation cannot be achieved without degrading the accuracy of the machine learning models, and 2) when the data used for training are largely biased, the training time automatically increases so as to find suitable learning parameters that help produce fair results. To address these shortcomings, we propose in this work a new framework that can largely mitigate the biases and discriminations in machine learning systems while at the same time enhancing the prediction accuracy of these systems. The proposed framework is based on conditional Generative Adversarial Networks (cGANs), which are used to generate new synthetic fair data with selective properties from the original data. We also propose a framework for analyzing databiases, which is important for understanding the amount and type of data that need to be synthetically sampled and labeled for each population group. Experimental results show that the proposed solution can efficiently mitigate different types of biases, while at the same time enhancing the prediction accuracy of the underlying machine learning model.

Additional Information: Le document est sur ArXiv (preprint - under review).
Funders: GRSNG / NSERC
PolyPublie URL: https://publications.polymtl.ca/51440/
Conference Title: 24th European Conference on Artificial Intelligence (ECAI 2019)
Conference Location: Santiago de Compostela, Spain
Conference Date(s): 2020-08-29 - 2020-09-08
Official URL: http://arxiv.org/abs/1905.09972
Date Deposited: 18 Apr 2023 15:01
Last Modified: 05 Apr 2024 11:55
Cite in APA 7: Abusitta, A., Aïmeur, E., & Abdul Wahab, O. (2020, August). Generative adversarial networks for mitigating biases in machine learning systems [Paper]. 24th European Conference on Artificial Intelligence (ECAI 2019), Santiago de Compostela, Spain (11 pages). http://arxiv.org/abs/1905.09972

Statistics

Stats are not available on this system.

Repository Staff Only

View Item View Item