Measuring the burden of (un) fairness using counterfactuals
In this paper, we use counterfactual explanations to offer a new perspective on fairness, that,
besides accuracy, accounts also for the difficulty or burden to achieve fairness. We first …
besides accuracy, accounts also for the difficulty or burden to achieve fairness. We first …
Ijuice: integer JUstIfied counterfactual explanations
Counterfactual explanations modify the feature values of an instance in order to alter its
prediction from an undesired to a desired label. As such, they are highly useful for providing …
prediction from an undesired to a desired label. As such, they are highly useful for providing …
JUICE: JUstIfied counterfactual explanations
Complex, highly accurate machine learning algorithms support decision-making processes
with large and intricate datasets. However, these models have low explainability …
with large and intricate datasets. However, these models have low explainability …
Orange Juice: Enhancing Machine Learning Interpretability
A Kuratomi Hernández - 2024 - diva-portal.org
In the current state of AI development, it is reasonable to think that AI will continue to expand
and be increasingly utilized across different fields, highly impacting every aspect of …
and be increasingly utilized across different fields, highly impacting every aspect of …
Hybrid feature tweaking: Combining random forest similarity tweaking with CLPFD
T Mattias Lindgren - Proceedings of the 2021 7th International …, 2021 - dl.acm.org
When using prediction models created from data, it is in certain cases not sufficient for the
users to only get a prediction, sometimes accompanied with a probability of the predictive …
users to only get a prediction, sometimes accompanied with a probability of the predictive …
[引用][C] Generating Counterfactual Explanations in Score-Based Classification via Mathematical Optimization
E Carrizosa, J Ramírez-Ayerbe… - 2022 - Technical Report IMUS, Sevilla …