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.

Baumann, J., Castelnovo, A., Crupi, R., Inverardi, N., Regoli, D. (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 (pp.1002-1013). Association for Computing Machinery (ACM) [10.1145/3593013.3594058].

Bias on Demand: A Modelling Framework That Generates Synthetic Data With Bias

Castelnovo, A;
2023

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.
paper
bias; fairness; moral worldviews; synthetic data;
English
6th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023 - 12 June 2023 through 15 June 2023
2023
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency
9798400701924
2023
1002
1013
open
Baumann, J., Castelnovo, A., Crupi, R., Inverardi, N., Regoli, D. (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 (pp.1002-1013). Association for Computing Machinery (ACM) [10.1145/3593013.3594058].
File in questo prodotto:
File Dimensione Formato  
Baumann-2023-FAccT-VoR.pdf

accesso aperto

Descrizione: Intervento a convegno - Research article
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 727.26 kB
Formato Adobe PDF
727.26 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/446479
Citazioni
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 6
Social impact