4 papers
Towards Fairness and Privacy: A Novel Data Pre-processing Optimization Framework for Non-binary Protected Attributes
Manh Khoi Duong, Stefan Conrad
The reason behind the unfair outcomes of AI is often rooted in biased datasets. Therefore, this work presents a framework for addressing fairness by debiasing datasets containing a…
Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes
Manh Khoi Duong, Stefan Conrad
Motivated by the recital (67) of the current corrigendum of the AI Act in the European Union, we propose and present measures and mitigation strategies for discrimination in tabula…
(Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers
Manh Khoi Duong, Stefan Conrad
Fairness metrics are used to assess discrimination and bias in decision-making processes across various domains, including machine learning models and human decision-makers in real…
Trusting Fair Data: Leveraging Quality in Fairness-Driven Data Removal Techniques
Manh Khoi Duong, Stefan Conrad
In this paper, we deal with bias mitigation techniques that remove specific data points from the training set to aim for a fair representation of the population in that set. Machin…