Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-29507| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Bias on demand : a modelling framework that generates synthetic data with bias |
| Authors: | Baumann, Joachim Castelnovo, Alessandro Crupi, Riccardo Inverardi, Nicole Regoli, Daniele |
| et. al: | No |
| DOI: | 10.1145/3593013.3594058 10.21256/zhaw-29507 |
| Proceedings: | Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency |
| Page(s): | 1002 |
| Pages to: | 1013 |
| Conference details: | 6th ACM Conference on Fairness, Accountability, and Transparency (FAccT), Chicago, USA, 12-15 June 2023 |
| Issue Date: | 15-Jun-2023 |
| Publisher / Ed. Institution: | Association for Computing Machinery |
| ISBN: | 979-8-4007-0192-4 |
| Language: | English |
| Subjects: | Bias; Fairness; Synthetic data; Moral worldview |
| Subject (DDC): | 006: Special computer methods |
| Abstract: | Nowadays, Machine Learning (ML) systems are widely used in various businesses and are increasingly being adopted to make decisions that can significantly impact people’s lives. However, these decision-making systems rely on data-driven learning, which poses a risk of propagating the bias embedded in the data. Despite various attempts by the algorithmic fairness community to outline different types of bias in data and algorithms, there is still a limited understanding of how these biases relate to the fairness of ML-based decision-making systems. In addition, efforts to mitigate bias and unfairness are often agnostic to the specific type(s) of bias present in the data. This paper explores the nature of fundamental types of bias, discussing their relationship to moral and technical frameworks. To prevent harmful consequences, it is essential to comprehend how and where bias is introduced throughout the entire modelling pipeline and possibly how to mitigate it. Our primary contribution is a framework for generating synthetic datasets with different forms of biases. We use our proposed synthetic data generator to perform experiments on different scenarios to showcase the interconnection between biases and their effect on performance and fairness evaluations. Furthermore, we provide initial insights into mitigating specific types of bias through post-processing techniques. The implementation of the synthetic data generator and experiments can be found at https://github.com/rcrupiISP/BiasOnDemand. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/29507 |
| Related research data: | https://github.com/rcrupiISP/BiasOnDemand |
| Fulltext version: | Published version |
| License (according to publishing contract): | CC BY 4.0: Attribution 4.0 International |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Data Analysis and Process Design (IDP) |
| Published as part of the ZHAW project: | Socially acceptable AI and fairness trade-offs in predictive analytics Algorithmic Fairness in data-based decision making: Combining ethics and technology |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2023_Baumann-etal_Bias-on-demand_ACM.pdf | 413.9 kB | Adobe PDF |  View/Open |
Show full item record
Baumann, J., Castelnovo, A., Crupi, R., Inverardi, N., & Regoli, D. (2023). Bias on demand : a modelling framework that generates synthetic data with bias [Conference paper]. Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 1002–1013. https://doi.org/10.1145/3593013.3594058
Baumann, J. et al. (2023) ‘Bias on demand : a modelling framework that generates synthetic data with bias’, in Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency. Association for Computing Machinery, pp. 1002–1013. Available at: https://doi.org/10.1145/3593013.3594058.
J. Baumann, A. Castelnovo, R. Crupi, N. Inverardi, and D. Regoli, “Bias on demand : a modelling framework that generates synthetic data with bias,” in Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, Jun. 2023, pp. 1002–1013. doi: 10.1145/3593013.3594058.
BAUMANN, Joachim, Alessandro CASTELNOVO, Riccardo CRUPI, Nicole INVERARDI und Daniele REGOLI, 2023. Bias on demand : a modelling framework that generates synthetic data with bias. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency. Conference paper. Association for Computing Machinery. 15 Juni 2023. S. 1002–1013. ISBN 979-8-4007-0192-4
Baumann, Joachim, Alessandro Castelnovo, Riccardo Crupi, Nicole Inverardi, and Daniele Regoli. 2023. “Bias on Demand : A Modelling Framework That Generates Synthetic Data with Bias.” Conference paper. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 1002–13. Association for Computing Machinery. https://doi.org/10.1145/3593013.3594058.
Baumann, Joachim, et al. “Bias on Demand : A Modelling Framework That Generates Synthetic Data with Bias.” Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, 2023, pp. 1002–13, https://doi.org/10.1145/3593013.3594058.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.