Výsledky vyhledávání - "Di Stefano, Pietro"

Report

Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms

Autor: Jones, Gareth P., Hickey, James M., Di Stefano, Pietro G., Dhanjal, Charanpal, Stoddart, Laura C., Vasileiou, Vlasios

Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which bias-miti

Externí odkaz: http://arxiv.org/abs/2010.03986

Zobrazit plný text záznamu

Report

Fairness by Explicability and Adversarial SHAP Learning

Autor: Hickey, James M., Di Stefano, Pietro G., Vasileiou, Vlasios

The ability to understand and trust the fairness of model predictions, particularly when considering the outcomes of unprivileged groups, is critical to the deployment and adoption of machine learning systems. SHAP values provide a unified framework

Externí odkaz: http://arxiv.org/abs/2003.05330

Zobrazit plný text záznamu

Report

Counterfactual fairness: removing direct effects through regularization

Autor: Di Stefano, Pietro G., Hickey, James M., Vasileiou, Vlasios

Building machine learning models that are fair with respect to an unprivileged group is a topical problem. Modern fairness-aware algorithms often ignore causal effects and enforce fairness through modifications applicable to only a subset of machine

Externí odkaz: http://arxiv.org/abs/2002.10774

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání