38 citations · 50 across the 10 of their papers we have counts for
5 papers · 1 filter
Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
Lisa Wimmer, Bernd Bischl, Ludwig Bothmann
The correct way to quantify predictive uncertainty in neural networks remains a topic of active discussion. In particular, it is unclear whether the state-of-the art entropy decomp…
Privilege Scores
Ludwig Bothmann, Philip A. Boustani, Jose M. Alvarez +3
Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an e…
mlr3summary: Concise and interpretable summaries for machine learning models
Susanne Dandl, Marc Becker, Bernd Bischl +2
This work introduces a novel R package for concise, informative summaries of machine learning models. We take inspiration from the summary function for (generalized) linear models…
Causal Fair Machine Learning via Rank-Preserving Interventional Distributions
Ludwig Bothmann, Susanne Dandl, Michael Schomaker
A decision can be defined as fair if equal individuals are treated equally and unequals unequally. Adopting this definition, the task of designing machine learning (ML) models that…
What Is Fairness? On the Role of Protected Attributes and Fictitious Worlds
Ludwig Bothmann, Kristina Peters, Bernd Bischl
A growing body of literature in fairness-aware machine learning (fairML) aims to mitigate machine learning (ML)-related unfairness in automated decision-making (ADM) by defining me…